# Safety & Policy > Every page below, concatenated. Each section gives the page title, its upstream source and its path in this repository. --- ## Claude Help Center Source: https://support.claude.com/en/articles/8324991-about-claude-pro-usage Path: 22-Safety-Policy/about-claude-pro-usage.md # Search for answers or browse by topic Search for articles... Uh oh. That page doesn’t exist. Try searching for your answer or just send us a message. --- ## Access engagement and adoption data with the Analytics API | Claude Help Center Source: https://support.claude.com/en/articles/13694757-access-engagement-and-adoption-data-with-the-analytics-api Path: 22-Safety-Policy/access-engagement-and-adoption-data-with-the-analytics-api.md 4. Access engagement and adoption data with the Analytics API # Access engagement and adoption data with the Analytics API The Analytics API gives Enterprise plan Primary Owners programmatic access to engagement and adoption data for their organization. Use it to build internal dashboards, track adoption trends, and feed Claude engagement data into your existing reporting tools. The Analytics API is available on Enterprise plans. Primary Owners can generate API keys to get started. ## How is this different from the analytics dashboard and Compliance API? All three options give you different views into your organization's data: The **Analytics dashboard** (accessed via **[Analytics](https://claude.ai/analytics/activity)**) shows visualized usage data in the product. It's the right tool for day-to-day monitoring when you don't need to integrate data elsewhere. The **Analytics API** returns the same aggregated usage and engagement metrics, but programmatically—so you can pull them into BI tools, map them against org charts, or automate reporting workflows. Data is aggregated per organization, per day. The **Compliance API** is for governance and auditing use cases. It gives you access to individual user actions, raw activity events, and conversation content. If you need aggregated engagement metrics for dashboards, rather than raw events for auditing, use the Analytics API. ------------------------------------------------------------------------ ## Get started To access the Analytics API, you need Primary Owner access to your Enterprise organization. Follow these steps: 1. Navigate to **[Analytics \> API keys](http://claude.ai/analytics/api-keys)**. 2. Find the **Access** toggle under **Analytics API** and toggle it on. 3. Click “+ Create key” to generate a new API key. Keep this key private—treat it like a password. 4. Use the key with the `x-api-key` header in your requests. For full authentication details, endpoint references, and code examples, refer to our **[Claude Enterprise Analytics API reference guide](../13-Enterprise-Admin/claude-enterprise-analytics-api-reference-guide.md)**. ------------------------------------------------------------------------ ## What data is available? The Analytics API includes five endpoints. All data is aggregated per organization, per day, and is available for up to the past 90 days (not before January 1, 2026). - **User activity**: Per-user engagement metrics including conversation counts, messages sent, projects created, files uploaded, artifacts created, skills used, connectors used, and Claude Code metrics like commits, pull requests, and lines of code. - **Activity summary**: Organization-wide daily, weekly, and monthly active user counts, along with seat utilization and pending invite counts. Supports date ranges up to 31 days per request. - **Chat project usage**: Conversation and user counts broken down by project, for Claude projects. - **Skill usage**: How many users are using each skill, with breakdowns for Claude and Claude Code sessions separately. - **Connector usage**: Which connectors your organization is using and how many unique users have used each one. ------------------------------------------------------------------------ ## Data limits All endpoints return data for a single date or date range. Data is only available after January 1, 2026, and for dates more than three days ago. The API has a default rate limit of 60 requests per minute. If this doesn't meet your organization's needs, reach out to your Anthropic Contact or our **[Sales team](https://claude.com/contact-sales)**. **Important:** If you are using Claude Code via **[Amazon Bedrock](https://support.claude.com/en/collections/4078537-amazon-bedrock)**, the Analytics API will not return data related to Claude Code. --- ## Age assurance on Claude | Claude Help Center Source: https://support.claude.com/en/articles/15171100-age-assurance-on-claude Path: 22-Safety-Policy/age-assurance-on-claude.md # Age assurance on Claude May 18, 2026 Claude, our consumer product, is only available to people over 18 years. You’ll need to confirm you’re 18 or over while setting up an account. When we detect signals that you may be under 18, we'll ask you to verify your age before you can continue using Claude. ## How this works We have safety systems in place to detect if people under 18 may be using Claude and we’ll disable accounts based on indicators of minor activity. You’ll have the option to verify your age using Yoti, a third-party age verification platform. A link for verification will be provided in the notification email. If you pass the age verification process, your account will be reinstated. ## Accepted age verification methods Yoti offers several ways to confirm you're 18 or over. You can choose whichever works best for you: - Facial age estimation: Take a selfie and Yoti's technology estimates your age. No ID document needed. - ID verification: Take a photo of your ID (such as a passport, driving license, or national ID card) and upload it from your device. See Yoti's **[full list of supported documents](https://developers.yoti.com/identity-verification/supported-documents)** for country-specific options. - Yoti’s Digital ID app: If you already have the Yoti app, share a verified "over 18" attribute from it. ## How we protect your data Yoti is an independently audited age verification provider for SOC2 compliance. Your selfie, document images, and any personal data are deleted by Yoti as soon as your age is checked. Anthropic never sees your ID or image; we receive only a pass/fail result and do not process or store any personal data from the verification. --- ## Anthropic MCP Directory Policy | Claude Help Center Source: https://support.claude.com/en/articles/11697096-anthropic-mcp-directory-policy Path: 22-Safety-Policy/anthropic-mcp-directory-policy.md # Anthropic MCP Directory Policy April 15, 2026 This policy has been consolidated into the [Anthropic Software Directory Policy](anthropic-software-directory-policy.md). Please refer to that document for current terms. --- ## Anthropic MCP Directory Terms and Conditions | Claude Help Center Source: https://support.claude.com/en/articles/11697081-anthropic-mcp-directory-terms-and-conditions Path: 22-Safety-Policy/anthropic-mcp-directory-terms-and-conditions.md # Anthropic MCP Directory Terms and Conditions March 16, 2026 This is a prior version of our terms. Please refer to [Anthropic Software Directory Terms](anthropic-software-directory-terms.md) for the most updated version. ## Terms for MCP Server Developers By submitting your MCP server for inclusion in any of Anthropic's Desktop Extensions or Integrations directories (individually or collectively, the “MCP Directory”), you (i) represent and warrant that you have all necessary rights to provide your MCP server to users and that your MCP server complies with all applicable laws and regulations; (ii) agree to indemnify and hold Anthropic harmless from any claims, damages, or liabilities arising from your MCP server or users' interaction with it; (iii) grant Anthropic a non-exclusive, royalty-free license to display your name, trademarks, logos, and other branding materials associated with your MCP server in the MCP Directory for the purpose of identifying and promoting your MCP server to users of the MCP Directory; and (iv) authorize Anthropic to perform security testing on your MCP server, to collect and use functional metadata about your MCP server to improve the Anthropic services, and to share such functional metadata with our users. If Anthropic elects to include your MCP server in the MCP Directory, you agree to continue implementing and maintaining quality and security standards for your MCP server that are consistent with [Anthropic's MCP Directory Policy](anthropic-mcp-directory-policy.md) (may be updated from time to time), and you acknowledge that failure to maintain these standards may result in removal from the MCP Directory. You further agree to implement and maintain a mechanism for receiving reports of security vulnerabilities from Anthropic and from third parties and to investigate such reports with a reasonable standard of care. You acknowledge that Anthropic has no obligation to include your MCP server in the MCP Directory and reserves the right to remove your MCP server at any time for any reason (including but not limited to violations of these terms, user complaints, security concerns, or changes to Anthropic's MCP Directory policies) without liability to you. You understand that inclusion in the MCP Directory does not create any partnership, employment, or agency relationship between you and Anthropic, nor does it grant you any rights to use Anthropic's name, trademarks, or intellectual property. Anthropic reserves the right to modify these Terms at any time without prior notice, and your continued submission or maintenance of an MCP server in the MCP Directory after any such changes constitutes your acceptance of the revised Terms. --- ## Anthropic Software Directory Policy | Claude Help Center Source: https://support.claude.com/en/articles/13145358-anthropic-software-directory-policy Path: 22-Safety-Policy/anthropic-software-directory-policy.md # Anthropic Software Directory Policy April 15, 2026 Anthropic allows users to discover high-quality Model Context Protocol servers, Skill folders, plugins, apps, and other software, containers, or data (“Software”) that work seamlessly within Claude through directories, repositories, surfaces, or similar offerings (collectively, “Directories”). We review submissions to our Directories to ensure they meet our standards for safety, security, and compatibility with Anthropic Services and other Software. We conduct both initial and ongoing reviews of Software, and may require developers to address compliance issues to continue being included in our Directories. All Software must maintain compliance with these requirements, including any future changes, to remain in our Directories. # 1. Safety and Security A. Software must not violate or facilitate violation of our [Usage Policy](https://www.anthropic.com/legal/aup). All Software must comply with our Universal Usage Standards and High-Risk Use Case requirements and with our policy on the [countries and regions Anthropic currently supports](https://www.anthropic.com/supported-countries). B. Software must not evade or enable users to circumvent Claude's safety guardrails, system instructions, or sandbox environments. C. Software must prioritize protecting user privacy and the privacy interests of third parties. Developers must take care to responsibly handle personal and other sensitive data, follow privacy best practices, and ensure compliance with applicable laws. D. Software must only collect data from the user’s context that is necessary to perform their function. Software must not collect extraneous conversation data, even for logging purposes. E. Software must not infringe on the intellectual property rights of others. F. Software must not query or extract data from Claude's memory, chat history, conversation summaries, or user-generated or uploaded files. # 2. Compatibility This section applies to Software that provides Claude with tools or capabilities through natural language descriptions, including MCP servers, Skill folders, and similar Software ("Instructional Software"). A. Instructional Software must define each tool or capability through narrow, unambiguous natural language that specifies what it does and when it should be invoked. B. Instructional Software tool or capability descriptions must precisely match actual functionality, ensuring the Instructional Software is called at correct and appropriate times. Descriptions must not include unexpected functionality or promise undelivered features. C. Instructional Software tool or capability descriptions must not create confusion or conflict with other Software in our Directories. D. Instructional Software must not intentionally call or coerce Claude into calling other external software, tools, databases, or resources unless requested and intended by a user. Similarly, Instructional Software tool or capability descriptions must not be written in a way that intentionally leads to other Software extraneously calling them. E. Instructional Software must not attempt to interfere with Claude calling tools from other software, tools, databases, or resources unless requested and intended by a user. F. Instructional Software must not direct Claude to dynamically pull behavioral instructions from external sources for Claude to execute. G. Instructional Software must not contain hidden, obfuscated, or encoded instructions. All behavioral guidance must be human-readable and clearly presented. # 3. Developer Requirements A. Developers of Software that collects user data or connects to a remote service must provide a clear, accessible privacy policy link explaining data collection, usage, and retention. Developers must provide Anthropic with links to all applicable privacy policies and ensure such policies are presented to users as required by law. B. Developers must provide verified contact information and support channels for users with product or security concerns. C. Developers must document how their Software works, its intended purpose, and how users can troubleshoot issues. D. Developers must provide a standard testing account with sample data for Anthropic to verify full Software functionality. E. Developers must provide at least three working examples of prompts or use cases that demonstrate core functionality. F. Developers must verify that they own or control any API endpoint, domain, or user interface their Software connects to, as well as any external resources it retrieves or renders. Plugins are an exception, and may connect to any Connector approved in the Software Directory. G. Developers must maintain their Software and address issues within reasonable timeframes. H. Developers must agree to our [Software Directory Terms](anthropic-software-directory-terms.md) and follow design guidelines Anthropic publishes applicable to Software. # 4. Unsupported Use Cases Unless otherwise expressly permitted by us in writing, we do not allow Software with certain capabilities into our Directories. We may revisit these restrictions as our Directories and Anthropic Services evolve. A. Software that transfers money, cryptocurrency, or other financial assets, or executes financial transactions on behalf of users. B. Software that uses AI models to generate images, video, or audio content. Design-focused software that uses AI models to create visual aids (such as slides, diagrams, charts, UI mockups, logos, or other design assets) are permitted. These servers may generate images as part of a design workflow, provided the developer does not offer standalone image generation as a primary service. C. Software that serves [advertisements](../19-Reference/claude-is-a-space-to-think.md), sponsored content, paid product placements, or exists primarily as an advertising or promotional vehicle. # 5. Additional Requirements for Model Context Protocol Servers A. MCP servers must gracefully handle errors and provide helpful feedback rather than generic error messages. B. MCP servers must be frugal with their use of tokens. The amount of tokens a given tool call uses should be roughly commensurate with the complexity or impact of the task. When possible, users should be given options to exclude unnecessary text in the response. C. MCP tool names must not exceed 64 characters. D. Remote MCP servers that connect to a remote service and require authentication must use secure OAuth 2.0 with certificates from recognized authorities. E. MCP servers must provide all applicable [annotations](../06-MCP-Tools/Spec-Archive/2025-11-25-schema.md#toolannotations) for their tools, in particular *readOnlyHint*, *destructiveHint*, and *title*. F. Remote MCP servers should support the [Streamable HTTP](../06-MCP-Tools/Spec-Archive/2025-03-26-basic-transports.md#streamable-http) transport. Servers may support [SSE](../06-MCP-Tools/Spec-Archive/2024-11-05-basic-transports.md#http-with-sse) for the time being, but in the future it will be deprecated. G. Local MCP servers must be built with reasonably current versions of all dependencies, including packages in *node_modules*. See prior version of this policy here: [Anthropic MCP Directory Policy](anthropic-mcp-directory-policy.md). --- ## Anthropic Software Directory Terms | Claude Help Center Source: https://support.claude.com/en/articles/13145338-anthropic-software-directory-terms Path: 22-Safety-Policy/anthropic-software-directory-terms.md # Anthropic Software Directory Terms March 16, 2026 By submitting your MCP server, Skill folder, plugin, app, or other software, container, or data (“Software”) for inclusion in any Anthropic directory, repository, surface, or similar offering (collectively, “Directories”), you represent and warrant to Anthropic that (i) you have and will maintain all necessary rights to provide your Software to users and to grant the rights set forth in these terms; (ii) your Software and the ordinary, intended use of your Software complies with all applicable laws and regulations and does not violate Anthropic’s Software Directory Policy (currently available at , as may be updated from time to time); (iii) any information you give us will be accurate and up-to-date; and (iv) if you or your Software collects or shares user information or other personal data, you will provide and adhere to a privacy policy for your Software, provide all applicable third-party privacy policies, and ensure all such policies clearly and accurately describe to users what user information you and third parties collect and how you and third parties use and share such information. You further (i) agree to indemnify and hold Anthropic harmless from any claims, damages, or liabilities arising from or related to your Software or users' interactions with it; (ii) grant Anthropic non-exclusive, royalty-free, worldwide licenses to reproduce, display, and distribute any descriptions of the Software and Software documentation provided by you or made available through the Software in connection with presenting the Software in the Directories and to display your name, trademarks, logos, and other branding materials associated with your Software in Directories for the purpose of identifying and promoting your Software, our Directories, and the Anthropic Services to our users and the public; and (iii) authorize Anthropic to review and test your Software in accordance with these terms, to collect and use functional metadata about your Software to improve the Anthropic Services, and to share such functional metadata with our users. Anthropic has no obligation to include your Software in any Directory and may remove or refuse to display any Software or its content from some or all Directories at any time for any reason (including but not limited to violations of these terms, user complaints, security concerns, or changes to Anthropic's Software Directory Policy) without liability to you. While Anthropic is not obligated to monitor your Software or its content, Anthropic may at any time review or test your Software for security vulnerabilities and to ensure quality and compliance with these terms, our Usage Policy, and our Software Directory Policy. If Anthropic elects to include your Software in one or more Directories, you agree to continue implementing and maintaining quality and security standards for your Software that are consistent with Anthropic's Software Directory Policy, as may be updated from time to time), and you acknowledge that failure to maintain these standards may result in your Software’s removal from some or all Directories. You further agree to implement and maintain a mechanism for receiving reports of security vulnerabilities from Anthropic and from third parties and to investigate such reports with a reasonable standard of care. You understand that inclusion of your Software in one or more Directories does not create any partnership, employment, or agency relationship between you and Anthropic, nor does it grant you any rights to use Anthropic's name, trademarks, or intellectual property. You will not make any statement regarding the Anthropic Services which suggests partnership with, sponsorship by, or endorsement by Anthropic without Anthropic’s prior written approval, and you will at all times comply with Anthropic’s [Trademark Guidelines](https://www.anthropic.com/legal/trademark-guidelines). Anthropic reserves the right to modify these terms at any time without prior notice, and your continued submission or maintenance of Software in one or more Directories after any such changes constitutes your acceptance of the revised terms. ------------------------------------------------------------------------ See prior version of these terms here: [Anthropic MCP Directory Terms and Conditions](anthropic-mcp-directory-terms-and-conditions.md). --- ## Buy usage bundles | Claude Help Center Source: https://support.claude.com/en/articles/14246112-buy-usage-bundles Path: 22-Safety-Policy/buy-usage-bundles.md # Buy usage bundles May 18, 2026 You can pre-purchase usage credits in bundles and save up to 30% compared to standard usage credit rates. Larger bundles come with bigger discounts, and your balance works across Claude, Claude Code, Claude Cowork, and third-party products. Usage bundles are available on Pro, Max, and Team plans. ------------------------------------------------------------------------ ## Where your balance works Your usage bundle balance is a single pool that applies across Claude, Claude Desktop, Claude Mobile (iOS and Android), Claude Code, Cowork, and third-party products that use your Claude account. ## Available bundles The discount you receive depends on the bundle size you purchase. Bigger bundles save you more. [TABLE] Individual Pro and Max plan subscribers can purchase up to \$2000 worth of discounted bundles per month. Any usage beyond this limit is billed at standard rates. On Team plans, Owners and Primary Owners can purchase up to \$3000 worth of discounted bundles per month. Any usage beyond this limit is billed at standard rates. Price and plans are subject to change at Anthropic's discretion. ------------------------------------------------------------------------ ## How to buy usage bundles You'll need usage credits enabled before you can purchase bundles. If you haven't set up usage credits yet, see the relevant guide for your plan: - **[Manage usage credits for paid Claude plans](https://support.claude.com/en/articles/12429409-manage-extra-usage-for-paid-claude-plans)** (Pro and Max) - **[Manage usage credits for Team and seat-based Enterprise plans](https://support.claude.com/en/articles/12005970-manage-extra-usage-for-team-and-seat-based-enterprise-plans)** (Team) Once usage credits are enabled: 1. Navigate to **[Settings \> Usage](https://claude.ai/settings/usage)**. 2. Click "Buy usage." 3. Select a bundle size. 4. Confirm your purchase. The discount is applied automatically at checkout. Your bundle balance appears in your usage dashboard and draws down as you use Claude beyond your plan's included limits. ------------------------------------------------------------------------ ## Frequently asked questions ### What happens if I reach the monthly purchase cap? You can still use usage credits beyond the cap, but any additional usage is billed at standard usage credit rates without a discount. ### Can I buy multiple bundles in the same month? Yes. You can purchase as many bundles as you'd like up to your monthly limit (\$2000 in value for Pro and Max plans, \$3000 in value for Team plans). ### Do usage bundles replace my plan's included usage? No. Your plan's included usage works the same as before. Bundle credits only apply after you've exceeded your plan's limits and are using usage credits. --- ## Can Claude produce images? | Claude Help Center Source: https://support.claude.com/en/articles/9002504-can-claude-produce-images Path: 22-Safety-Policy/can-claude-produce-images.md # Can Claude produce images? March 16, 2026 Claude doesn’t generate photos or illustrations the way image-generation tools do. Claude can, however, build diagrams, charts, and interactive visuals directly in your conversation to assist with your understanding. These are generated using HTML and SVG—so you can interact with them, ask follow-up questions, and have Claude adjust them as you go. This feature is in beta on Claude web and desktop. For additional details, see **[Custom visuals in chat](https://support.claude.com/en/articles/13979539-custom-visuals-in-chat)**. Claude can also view and analyze images you upload. For more, see **[Uploading files to Claude](https://support.claude.com/en/articles/8241126-uploading-files-to-claude)**. --- ## Child safety guidance for developers | Claude Help Center Source: https://support.claude.com/en/articles/15591275-child-safety-guidance-for-developers Path: 22-Safety-Policy/child-safety-guidance-for-developers.md # Child safety guidance for developers June 26, 2026 ## **Our commitments to child safety** Anthropic takes a Safety by Design approach to child safety. We are signatories to **[Thorn and All Tech Is Human’s Safety by Design Principles for Generative AI](../19-Reference/child-safety-principles.md)** and report on our progress in the **[Transparency Hub](https://www.anthropic.com/transparency/voluntary-commitments)**. In practice, this means that we apply safety training designed to make our models refuse requests that sexualize or endanger minors, operate detection and monitoring systems across our services, and report apparent CSAM and other forms of child exploitation to the National Center for Missing & Exploited Children (NCMEC). Our first-party consumer services are restricted to users 18 years and older, and Claude does not produce photorealistic image or video output. These protections apply across our platform. Because you control your product's design, user base, and content flows, you are best positioned to address risks specific to your deployment. ## **Your obligations under Anthropic's Usage Policy** All developers building on Anthropic's API are required to comply with our **[Usage Policy](https://www.anthropic.com/aup)**, which prohibits using our products or services to compromise children's safety. This includes, among other things, creating, distributing, or promoting CSAM, including AI-generated CSAM; facilitating grooming, trafficking, sextortion, or other exploitation of a minor; and sexualizing minors in any context, including fiction or roleplay. These obligations apply regardless of your platform's size or use case. While you may already prohibit this activity, your end users or customers may upload CSAM, elicit sexualized content involving minors, or use outputs to facilitate grooming or sextortion. You are responsible for implementing appropriate safeguards against these risks on your deployment. We monitor API usage for violations of the Usage Policy and take enforcement action consistent with our policies and legal obligations. Additionally, if your product allows minors to interact directly with our models, please refer to our **[Guidelines for Organizations Serving Minors](../13-Enterprise-Admin/responsible-use-of-anthropic-s-models-guidelines-for-organizations-serving-minors.md)**, which sets out the additional safeguards Anthropic requires for that audience. This guidance covers a range of possible measures, including but not limited to age verification systems, content moderation and filtering, monitoring and reporting mechanisms, and regulatory compliance and disclosure requirements. Whether you've received a notification from Anthropic about prohibited content or are proactively building out your safeguards, the resources below can help you get oriented in standing up detection, reporting, and response infrastructure appropriate to your platform. ## **Building a child safety program** There is no single correct architecture for a child safety program. The viable approach depends on your platform; its size; the surfaces where users can engage, submit, or generate content; and your jurisdiction. Many platforms have already built prevention and response capabilities suited to their own contexts, and the field has developed shared guidance, tooling, and reporting infrastructure that newer programs can draw on. The organizations below offer resources that many platforms use as a starting point. Anthropic does not require you to use any specific vendor or program. **Design principles.** Thorn and All Tech Is Human have published **[Safety by Design for Generative AI](https://www.thorn.org/blog/generative-ai-principles/)**, a set of principles and practical mitigations for preventing child sexual abuse across the develop, deploy, and maintain phases of an AI product. Anthropic is a **[signatory](../19-Reference/child-safety-principles.md)** to these principles, and we encourage developers building on our models to consider them when designing their own safeguards. **Detection & blocking services.** If your deployment allows users to upload or generate images or videos, or interact with other users, you can implement detection on your own infrastructure. Organizations may choose to build custom classifiers tailored to their threat model, though for many, a vendor or partner solution may be the more practical path. There are several providers that offer hash-matching, image, video, or text classifier solutions. For example, one widely deployed option is **[Thorn's Safer](https://safer.io/solutions/)**, which provides hash-matching against known CSAM and classifiers for novel material and grooming signals. The **[Internet Watch Foundation](https://www.iwf.org.uk/our-technology/our-services/)** (IWF) offers its member companies a **[suite of services](https://www.iwf.org.uk/our-technology/our-services/)** for detecting, blocking, and responding to CSAM on their platforms, including hash lists and a URL blocklist. The Tech Coalition's Pathways program (described below) can help companies evaluate and access detection options suited to their platform. **Program development and operational guidance.** The **[Tech Coalition](https://technologycoalition.org/)** is an industry alliance focused on preventing online child sexual exploitation and abuse. Its free **[Pathways](https://technologycoalition.org/programs/pathways/)** program is designed for startups and small to mid-sized platforms and provides templates for building a child safety program, guidance on CSAM detection and NCMEC reporting, insight into global regulatory requirements, and support on emerging risks such as financial sextortion and AI-generated harms. Anthropic is a Tech Coalition member. You can contact the **[Tech Coalition team](https://support.claude.com/cdn-cgi/l/email-protection#d3beb793a7b6b0bbbdbcbfbcb4aab0bcb2bfbaa7babcbdfdbca1b4)** for an initial consultation. **Reporting.** US-based platforms with actual knowledge of apparent CSAM are legally required to report to **[NCMEC's CyberTipline](https://report.cybertip.org/)**. Platforms can **[register with NCMEC](https://esp.ncmec.org/registration)** to gain access to the CyberTipline reporting system, and NCMEC publishes additional **[legal resources](https://www.missingkids.org/gethelpnow/support/legalresources)** on reporting obligations. Platforms operating in other jurisdictions should consult local reporting requirements; INHOPE maintains a **[directory of national hotlines](https://www.inhope.org/EN#hotlineReferral)**. As you build your program, consider incorporating logging for the purposes of transparency reporting. *This page is provided for informational purposes only and does not constitute legal advice or endorsement by Anthropic. Consult your own legal counsel regarding your specific obligations.* --- ## Claude Code usage analytics | Claude Help Center Source: https://support.claude.com/en/articles/12157520-claude-code-usage-analytics Path: 22-Safety-Policy/claude-code-usage-analytics.md # Claude Code usage analytics July 1, 2026 This feature allows Console users and owners of Team and Enterprise plans to monitor how their organization uses Claude Code, tracking productivity metrics and adoption patterns across teams. Claude Code usage analytics are available to: - **Team plans:** Owners and Primary Owners - **Enterprise plans:** Owners, Primary Owners, and Admins (requires a Chat + Claude Code seat for usage-based plans or Premium seat for seat-based plans) - **API Console:** Admin, Billing, and Developer roles ## Access Claude Code analytics ### Team and Enterprise plans 1. Log in to your Owner or Primary Owner account. 2. Click your initials or name in the lower left corner. 3. Navigate to **[Analytics \> Claude Code](https://claude.ai/analytics/claude-code)**. 4. Select the “Usage” or “Value” tab. ### API Console users 1. Log in to your **[Claude Console account](../04-API-Reference/Other/usage-limits.md)**. 2. Expand the left side panel. 3. Click “Claude Code” under **Analytics**. 4. View Claude Code usage analytics on **[Settings \> Claude Code](../04-API-Reference/Other/usage-limits.md)**. ------------------------------------------------------------------------ ## Usage tab The **Usage** tab displays the following metrics for your organization. Data on this tab refreshes daily. ### Organization-level metrics - **Lines of code accepted**: Total lines of code your team has accepted from Claude Code suggestions. - **Suggestion accept rate**: Percentage of Claude Code suggestions that your team accepts. - **Activity trends**: Daily view of active users and sessions over time. - **Lines accepted over time**: Daily breakdown of accepted code lines. - **Top commands**: The Claude Code commands used most often across your organization. ### User-level metrics **Individual usage**: View each team member's email address and their total lines of code accepted for the current month. You can search for specific users or click the “Export” button to generate a CSV of members’ email addresses and total lines of code. ------------------------------------------------------------------------ ## Value tab The **Value** tab summarizes usage and cost data to help you understand what Claude Code is returning to your organization at a glance. - **Estimated productivity lift** - **Cost per commit** - **Estimated annual value** Every formula used on this tab is shown inline. Click any input to adjust it to match your organization's assumptions, and the estimates recalculate. ------------------------------------------------------------------------ ## Contribution metrics (beta) Contribution metrics are a new feature in public beta that helps Team and Enterprise organizations measure how Claude Code affects engineering velocity. By connecting to your organization's GitHub account, these metrics track code shipping activity with and without Claude Code, so you can see where it's making a difference. Contribution metrics require GitHub Cloud and are not available to Console users at this time. For a more in-depth look at contribution metrics, see **[our Claude Code docs](../13-Enterprise-Admin/analytics.md#enable-contribution-metrics)**. ### Set up contribution metrics Contribution metrics require a few steps beyond the base analytics setup: 1. Install the **[Claude GitHub App](https://github.com/apps/claude)** on your organization's GitHub account. 2. Log in with an Owner or Primary Owner account. 3. Navigate to **[Organization settings \> Claude Code](https://claude.ai/admin-settings/claude-code)**. 4. Enable the Claude Code analytics feature if you haven't already. 5. Toggle on **GitHub analytics**. 6. Select the GitHub organization(s) you want included in the comparison. After setup, metrics begin populating automatically. Allow up to 24 hours for data to appear. The dashboard currently processes data once daily. If you see "GitHub app required. Install the GitHub app to view analytics," the GitHub App hasn't been installed yet. If the app is authenticated but no data appears, confirm the GitHub App is installed and that your team has started using Claude Code. ### Available contribution metrics Once enabled, the following metrics appear in your Claude Code analytics dashboard: 1. **Pull requests merged**: Total PRs merged with and without Claude Code assistance, at both the organization and user level. 2. **Lines of code committed**: Total lines committed with and without Claude Code assistance, at both the organization and user level. 3. **Pull requests opened per user**: Individual PR activity across your team. Data is collected by correlating Claude Code session activity with GitHub commits and pull requests. ------------------------------------------------------------------------ ## Data reset and availability Usage metrics display data for the current calendar month and reset at the beginning of each month. Historical data visualization shows daily granularity for tracking trends over time. ## Use analytics to optimize Claude Code adoption Review your organization's code acceptance rate to understand if teams are finding Claude Code's suggestions valuable. If rates are lower than expected, consider providing additional training on effective prompting techniques. Monitor individual usage patterns to identify power users who can share best practices with the broader team, or to spot team members who might benefit from additional support. Track activity trends to understand when your team uses Claude Code most effectively and ensure adequate seat allocation during peak periods. ------------------------------------------------------------------------ ## Frequently asked questions ### I'm using an individual paid plan; how can I access usage analytics for Claude Code? Claude Code usage analytics are not available to individual Pro or Max plans at this time. ### I'm looking for a specific user but they're missing from the reports. If you notice that a specific user isn't showing up in your analytics, you should have them update Claude Code to the most recent version. The first Claude Code version to support this feature is **version 2.0.28**, so users should run `claude update` to manually update Claude Code if needed. ### Where can I find more information? See **[Analytics](../13-Enterprise-Admin/analytics.md)** in our Claude Code docs for more information. --- ## Claude for Teachers: your data and our terms | Claude Help Center Source: https://support.claude.com/en/articles/15926041-claude-for-teachers-your-data-and-our-terms Path: 22-Safety-Policy/claude-for-teachers-your-data-and-our-terms.md # Claude for Teachers: your data and our terms August 28, 2026 ## Overview **[Claude for Teachers](../18-Industry-UseCases/teachers.md)** is free for verified US K-12 educators, whether you sign up as an individual teacher or your school or district sets up an organization for everyone. Qualifying teachers or organizations that sign up by June 30, 2027 get a full year of free access. This offering includes free access to Claude Pro features, teaching skills built for lesson planning and differentiation, a connection to curriculum mapped to academic standards in all 50 states, and terms written for K-12. This page explains the **[U.S. K-12 Terms of Service](https://www.anthropic.com/legal/k12-terms)**, **[US K-12 Public Sector Addendum](https://anthropic.com/legal/k12-addendum)**, and the **[U.S. K-12 Data Processing Agreement](https://www.anthropic.com/legal/k12-dpa)**. ## Who is this for? Claude for Teachers is for educators working in US K-12 schools and districts: classroom teachers, instructional coaches, specialists, interventionists, librarians, counselors, and other certificated staff. It's available two ways: - **Individual educators** verify with a school email for free access, and accept the K-12 terms themselves. - **Schools and districts** have an authorized administrator set up a free Claude Enterprise organization. Teachers join through district single sign-on, and the school or district accepts the K-12 terms once for everyone, including the DPA and, for public schools and districts, the Public Sector Addendum. ## What you get Claude for Teachers includes Pro-level features, with Claude Code and Claude Cowork. It also includes: - **The Learning Commons connector**, which gives Claude academic standards in all 50 states, the prerequisite skills beneath them, and curriculum context - **Teaching skills** for lesson planning and differentiation, grounded in learning science - **Education connectors** from partners including MagicSchool, TeachFX, and Canva for Education - **FERPA-aligned protections** **Important:** Claude for Teachers is not for students. It's an educator-only offering. If you're a student over 18 or using Claude outside your work as an educator, Claude is governed by our Consumer Terms of Service instead. **Important:** If your district has set up a Claude for Teachers organization, the K-12 terms your district accepted govern your use of Claude within that organization. ## K-12 privacy and terms ### We don't train on your conversations Anthropic will not use your inputs or outputs to train our models. You keep all rights to your Inputs. You own your Outputs. ### Protect your data When you create a Claude for Teachers account, you are the “Controller” of the data submitted. You control how the data is used, and may access or delete that data at any time. Anthropic acts as a “Processor” of the data on your behalf. We only process the data as instructed by you in order to provide the Claude service. This means: - Student data stays under your (or your district's) control, and Anthropic uses it only to provide the service. - Anthropic doesn't sell or share student data, and doesn't use it for advertising, marketing, or to build a profile of a student. - Anthropic doesn't collect student data directly from students. Student accounts aren't part of Claude for Teachers. - Requests from students or parents about their information are forwarded to you or your district to handle, and Anthropic helps you respond. **Note:** Claude for Teachers provides a FERPA-configured setting to process student data. Whether and how identifiable student information may be used in Claude for Teachers is determined by your school or district's policies, not by Anthropic. If you're on an individual teacher account and have not received school or district authorization to make that decision, don't include identifiable student information in Claude for Teachers. ### Security AES-256 encryption at rest. TLS 1.2 or better in transit. Multi-factor authentication on every system holding your data, with access limited to staff who need it. Annual third-party audits and penetration testing. Certifications, including SOC 2, at our **[Trust Center](https://trust.anthropic.com/)**. Anthropic gives advance notice before adding a new subprocessor, with 15 days to object, and districts can audit Anthropic's controls once a year. ### Delete your data You control your conversations and can delete your chats anytime from your dashboard. More information on data deletion can be found here: **[Can you delete data that I sent via Team and Enterprise plans?](https://support.claude.com/en/articles/9796617-can-you-delete-data-that-i-sent-via-team-and-enterprise-plans)** Your district's admins can also delete any member's data through the Compliance API when district policy requires it. If your district leaves Claude, Anthropic returns your district's data on request and deletes its copies within 30 days, except where the law requires retention. ## About your Claude for Teachers account ### Individual teacher accounts When you verify, your account moves onto a Claude for Teachers plan—a free Claude for Teams plan for verified educators. It comes with educator-specific terms and a data processing agreement, your chats and files aren't used to train our models, and student-data protections are built in. Your usage limits are higher than a standard free account—enough for everyday classroom work like lesson planning, quizzes, and parent communication. Some Team plan features are turned off for Claude for Teachers. You won't see billing and seat purchasing, **[member invitations and management](../17-Billing-Plans/managing-members-on-team-and-enterprise-plans.md)**, roles and permissions, SSO and domain capture, spend controls, usage credits, or premium seats. For questions, **[reach out to our Support team](https://support.claude.com/en/articles/9015913-how-to-get-support)**. ### School and district organizations When your school or district sets up Claude for Teachers, teachers are members of a **[Claude Enterprise organization](../15-Claude-AI-Features/set-up-claude-for-teachers-for-your-school-or-district.md)** that the district owns and manages. What's different from an individual Claude for K-12 Teachers account: - **One set of terms.** Your district accepts the K-12 terms and DPA once for everyone. - **District sign-in.** You sign in with your district login (single sign-on) rather than creating your own account. Once your district verifies its email domain, new personal Claude accounts can't be created with a district email address. - **Admin controls.** Your district's admins decide which features, models, and connectors you can use, and can manage members and roles. - **Admin access to content.** Your district's primary owner can turn on the Compliance API and use it to read or delete any member's chats, files, and projects. - **Same usage allowance.** You get the same rolling five-hour and weekly limits as an individual Claude for Teachers account. **Note:** Public schools, districts, and charter schools also accept the **[US K-12 Public Sector Addendum](https://anthropic.com/legal/k12-addendum)**, which adapts the terms for public entities—for example, your state's law governs, and arbitration and indemnification will not apply when prohibited by state law. It doesn't change how student data is handled, and it doesn’t apply to individual teacher accounts. ## Get started Teachers, schools, and districts can all get started for free at **[Claude for Teachers](../18-Industry-UseCases/teachers.md)**. Sign up by June 30, 2027 for your full year of free access. --- ## Claude March 2026 usage promotion | Claude Help Center Source: https://support.claude.com/en/articles/14063676-claude-march-2026-usage-promotion Path: 22-Safety-Policy/claude-march-2026-usage-promotion.md # Claude March 2026 usage promotion We're offering a limited-time promotion that doubles usage limits for Claude users outside 8 AM-2 PM ET / 5-11 AM PT / 12-6 PM GMT on weekdays. This promotion is available for Free, Pro, Max, and Team plans. Enterprise plans are not included in this promotion. ## What is the promotion? From March 13, 2026 through March 28, 2026, your five-hour usage is doubled during off-peak hours (outside 8 AM-2 PM ET / 5-11 AM PT / 12-6 PM GMT) on weekdays). Usage remains unchanged from 8 AM-2 PM ET / 5-11 AM PT / 12-6 PM GMT on weekdays. ## Eligibility No action is required to participate. If you’re on an eligible plan, the doubled usage is automatically applied. ## Where does this apply? The 2x usage increase applies across the following Claude surfaces: - Claude (web, desktop, and mobile) - Cowork - Claude Code - Claude for Excel - Claude for PowerPoint ## Frequently asked questions ### Do I need to do anything to get the extra usage? No. The promotion applies automatically. You’ll see higher limits reflected in your usage outside 8 AM-2 PM ET / 5-11 AM PT / 12-6 PM GMT on weekdays without any changes to your account settings. ### Does bonus usage count against my weekly usage limit? No. The additional usage you get during off-peak hours doesn’t count toward any weekly usage limits on your plan. ### What happens when the promotion ends? After March 28, 2026, usage limits return to their standard levels at all hours. There’s no change to your plan or billing. ## Terms and conditions This offer is valid from March 13, 2026 through March 28, 2026 at 11:59 PM PT. It applies to Free, Pro, Max, and Team plans only and excludes Enterprise plans. This offer has no cash value and is not transferable. It may not be combined with other offers. --- ## Configure a custom OpenTelemetry collector for Office agents | Claude Help Center Source: https://support.claude.com/en/articles/14447276-configure-a-custom-opentelemetry-collector-for-office-agents Path: 22-Safety-Policy/configure-a-custom-opentelemetry-collector-for-office-agents.md # Configure a custom OpenTelemetry collector for Office agents August 5, 2026 You can route full audit telemetry from Office agents to your own OpenTelemetry (OTEL) collector. This gives your organization complete control over retention, encryption, and integration with your SIEM or observability platform. This guide covers how to enable a custom collector, what data you'll receive, and the full span schema reference. Custom OTEL collectors are available to Claude Enterprise organizations and to direct-provider deployments (Amazon Bedrock, Google Vertex AI, or a gateway). ## What you'll receive When you configure a custom collector, Office agents send trace data covering every user turn. Each turn produces a tree of spans capturing the prompt, model calls, tool executions, file uploads, and context compaction events. Your collector receives all span attributes, including those carrying user-generated content (prompt text, tool inputs and outputs, document URLs, and filenames). No attributes are redacted or filtered. Assistant response text is not included in the emitted span data. Your organization owns this data. **Important:** Metrics aren't sent to custom collectors. The `office_agent.*` counter namespace routes to Anthropic only. However, every counter increment also appears as a span event on the active span, so the same signals are available in your traces. Telemetry is sent via OTLP/HTTP to your endpoint at `{your_url}/v1/traces`. gRPC isn't supported because the add-in runs in an Office WebView. ------------------------------------------------------------------------ ## Enable a custom collector Setup differs depending on how your organization authenticates with Claude. **Important:** When a custom endpoint is configured, telemetry goes exclusively to your collector. Spans aren't dual-sent to Anthropic. ### Claude Enterprise (OAuth) organizations An organization administrator sets the collector endpoint in the Claude.ai admin console under **[Organization settings \> Office agents](https://claude.ai/admin-settings/office-agents)**. The setting applies organization-wide. [TABLE] The protocol must be HTTP-based OTLP. gRPC is rejected at configuration time. ### Direct provider deployments (Amazon Bedrock, Google Vertex AI, gateway) For deployments that authenticate against your own model provider rather than Claude.ai, the collector endpoint is supplied through one of three configuration channels. All three use the same two keys. **Recommended:** Use the **[claude-for-msft-365-install plugin](https://github.com/anthropics/financial-services/tree/main/claude-for-msft-365-install)** for Claude Code. It walks you through generating the manifest, registering Entra extension attributes, and standing up a bootstrap endpoint with `otlp_endpoint` and `otlp_headers` pre-wired. The three channels below are documented for reference and manual setup. [TABLE] If `otlp_endpoint` is unset or empty, no custom collector is configured and the add-in falls back to default behavior. **Note:** These configuration channels apply to Microsoft Office deployments only. Google Workspace add-ins are configured separately. **Channel 1: Manifest URL parameter** Append the keys as query string parameters to the taskpane URL in your custom add-in manifest: `https:///taskpane.html?otlp_endpoint=https://otel-collector.your-domain.com&otlp_headers=Authorization=Bearer%20` URL-encode the values. This applies the configuration to every user who installs the manifest. **Channel 2: Azure Entra ID directory extension** For per-user configuration, register the keys as Entra ID directory extension attributes and assign them via Microsoft Graph. The add-in reads them from the user's ID token using Nested App Authentication (NAA). The claim names in the issued ID token follow Azure's directory extension format: [TABLE] Set these per-user with a Graph PATCH against the user object. Azure encodes directory extension values as single-element arrays in the ID token; the add-in unwraps them automatically. This channel requires `entra_sso=1` in the manifest URL parameters to enable NAA token acquisition. **Channel 3: Bootstrap endpoint response** If your deployment uses a bootstrap endpoint (a JSON endpoint your organization hosts that the add-in calls at startup), include the keys in the response body: { "otlp_endpoint": "https://otel-collector.your-domain.com", "otlp_headers": "Authorization=Bearer " } The bootstrap endpoint URL itself is configured via `bootstrap_url` in either the manifest URL parameters or an Entra `extn.bootstrap_url` claim. If an Entra ID token was acquired, it is passed to the bootstrap endpoint as a Bearer authorization header so your endpoint can authenticate the user before returning per-user configuration. **Precedence** When multiple channels supply a value, later channels override earlier ones: manifest parameters are read first, then Entra claims, then the bootstrap response. The bootstrap response wins. If you haven't already, the fastest path is the **[claude-for-msft-365-install plugin](https://github.com/anthropics/financial-services/tree/main/claude-for-msft-365-install)**. ------------------------------------------------------------------------ ## Deployment modes Custom collector export is available on both deployment modes: - Claude.ai Enterprise (OAuth): full audit trail including user identity (`user.email`, `user.account_uuid`, `organization.id`), MCP server metadata, and file upload records. - Direct provider (Bedrock, Vertex AI, gateway): core audit trail (prompts, tool inputs and outputs, document URLs) but no user identity, no MCP metadata, and no file upload spans. User attribution requires correlating `session.id` against your own identity provider logs. The core audit payload is identical in both modes. Direct provider deployments lack Claude.ai account context, so attributes derived from the Claude.ai user or organization profile are absent. See the `[claude.ai-only]` tags in the span schema below for the complete list. ## Surface and vendor labels Every span includes two labels identifying which Office application and platform generated it. Use these as your primary dimensions for filtering and dashboards. [TABLE] ------------------------------------------------------------------------ ## Span reference Each user turn produces a parent/child tree of up to five span types. Attributes marked \[content\] carry user-generated data; these form your audit payload. Attributes marked \[`claude.ai-only`\] are populated only when the user signs in with a Claude account; they are absent on Bedrock, Vertex AI, and gateway deployments. Absent attributes are omitted from the span entirely (no key with a null value). The `file.upload` span and all `mcp.*` attributes are also \[`claude.ai-only`\], since file upload and MCP server connections are Claude platform features. For direct provider deployments, user identity should be correlated via `session.id` and `document.url`, joined against your identity provider's session logs. ### Resource attributes These attributes appear on every span: [TABLE] ### agent.query (root span) One span per user turn. This is the root of the span tree and carries session identity, document context, and MCP server status. SpanKind: INTERNAL. [TABLE] ### agent.stream One span per API call to Claude, as a child of the query span. SpanKind: CLIENT. [TABLE] **Note on prompt caching:** The add-in requests prompt caching unconditionally. The `cache_read_tokens` and `cache_creation_tokens` attributes are set from the provider's API response and are omitted when the response doesn't include them. Prompt caching is available for Claude Platform; as of this writing, Amazon Bedrock and Google Vertex AI don't yet return these fields through the client the add-in uses. When support lands on your provider, these attributes will begin appearing automatically. ### agent.tool_execution One span per tool call, as a child of the stream span. SpanKind: INTERNAL. This is the primary record of what actions the model took against the document. [TABLE] **Note:** The `tool.accept_decision` attribute records how the permission decision was made: `manual` (the user approved this specific action), `auto_accept` (the user had previously granted standing approval), or `deferred` (the action was queued for later review). Use this to audit approval patterns across your organization. ### agent.compaction One span per conversation auto-summarization, fired when context approaches the window limit. SpanKind: CLIENT. [TABLE] This span also carries `agent.surface`, `agent.vendor`, `session.id`, `user.email [claude.ai-only]`, `user.bucket [claude.ai-only]`, `office.platform`, and `office.version`, duplicated from the root span so you can query compaction events independently. ### file.upload \[claude.ai-only\] One span per individual file upload, as a child of the query span. SpanKind: CLIENT. This span type only appears when users sign in with a Claude.ai account. File upload isn't available on direct provider deployments. [TABLE] ------------------------------------------------------------------------ ## Span events Span events are timestamped markers attached to the spans above. They capture lifecycle transitions and counter-equivalent signals. - `agent.query`: exception {exception.type}; file_upload {file_id, mime_type, content_category} - `agent.stream`: first_token; stream_complete; stream_error {exception.type} - `agent.tool_execution`: tool_init; tool_run; tool_result; tool_error {error_type} - `agent.compaction`: compaction_start; compaction_complete; compaction_error {exception.type} - `file.upload`: exception {exception.type} Every internal product counter also records a span event with the same name on the currently active span, providing the equivalent of the metrics stream within your trace data. The `office_agent.token.usage` event is emitted on each `agent.stream` span, once per non-zero token type, with attributes {token_usage.type: input \| output \| cacheRead \| cacheCreation, token_usage.model, token_usage.token_count}. This mirrors the `*.token.usage` counter shape emitted by other Anthropic products, so a single collector can aggregate token cost across products by grouping on `service.name`. ------------------------------------------------------------------------ ## Surface-specific behavior The telemetry schema is consistent across all surfaces. These are the differences: - Sheets (Excel): `agent.tool_execution` spans include `sheet.cells_read`, `sheet.cells_written`, and `sheet.cells_copied` attributes. `office_agent.cell_edit_collision_total` span events appear when a user is mid-cell-edit while a tool tries to write. - Documents (Word): document-edit funnel events track the edit lifecycle: `office_agent.doc_edit_received_total`, `office_agent.doc_edit_parsed_total`, `office_agent.doc_edit_applied_total`, `office_agent.doc_proposed_edit_reviewed_total`. No `sheet.cells_*` attributes. - Slides (PowerPoint): no surface-specific attributes or events beyond the common schema. - Mail (Outlook): no surface-specific attributes or events beyond the common schema. ------------------------------------------------------------------------ ## Reconstructing a user session ### Claude.ai deployments - Filter spans by `user.email` (or `user.account_uuid`) and `session.id`. - Order `agent.query` spans by start timestamp; each is one user turn. - For each turn, `user.message` is the prompt and `document.url` is the file being worked on. - Child `agent.tool_execution` spans, ordered by timestamp, are the actions taken: `tool.input` is what was attempted, `tool.output` is the result, `tool.accept_decision` records whether the user explicitly approved. ### Direct provider deployments The add-in has no Claude.ai user identity in this mode, so spans carry no `user.email` or `user.account_uuid`. To attribute activity to a user: - Filter spans by `session.id` to isolate one continuous add-in session. - Use `document.url` to identify the file being worked on. - Correlate the session against your identity provider's logs: Entra sign-in events, gateway access logs, or your bootstrap endpoint's request log (which receives the user's Entra ID token as a Bearer header). - Once a session is attributed to a user, the per-turn reconstruction is identical: agent.query spans ordered by timestamp, with `user.message`, `tool.input`, `tool.output`, and `tool.accept_decision` providing the audit trail. This produces a complete, ordered transcript of the interaction in both deployment modes. --- ## Configuring session security settings | Claude Help Center Source: https://support.claude.com/en/articles/13163631-configuring-session-security-settings Path: 22-Safety-Policy/configuring-session-security-settings.md # Configuring session security settings May 7, 2026 This feature is available to Admins and Owners of Enterprise plans and Console Admins. Session duration controls allow Enterprise and Console Admins to set a maximum session length for all users in their organization. When enabled, users will need to sign in again after the specified period, even if they've been actively using Claude. This helps protect your organization by limiting how long a compromised session could remain valid. ## Enabling session length settings ### For Enterprise Admins 1. Log in to your Enterprise organization as an Admin or above. 2. Navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**. 3. Locate the **Session security** section. 4. Click “Enable” next to **Shortened session length**, then select a duration from the dropdown: 1 day, 7 days, 14 days, or 28 days. 5. Confirm your selection by clicking “Enable.” ### For Console Admins 1. Log in to your Console account as an Admin. 2. Navigate to **[Settings \> Organization and access](../04-API-Reference/Other/usage-limits.md)**. 3. Locate the **Session security** section. 4. Click “Enable” next to **Shortened session length**, then select a duration from the dropdown: 1 day, 3 days, or 7 days. 5. Confirm your selection by clicking “Enable.” ### What happens after enabling shortened session length? - Existing sessions older than the selected duration will expire immediately. - Other active sessions will expire no later than the selected duration. - Users whose sessions expire will be directed to sign in again. ## Updating session duration You can change the session duration at any time by selecting a new value from the dropdown. If you select a shorter duration: - Sessions older than the new duration will expire immediately. - Sessions scheduled to expire beyond the new duration will have their expiration shortened accordingly. ## Disabling session length settings To disable session duration, select "Disable" next to **Shortened session length**. Existing active sessions will continue to expire at their scheduled time. New sessions will return to default behavior, where sessions remain active as long as the user stays active. ## Users in multiple organizations If a user belongs to multiple organizations with different session duration settings, the shortest duration will be applied. For example, if a user is a member of Organization A (7-day limit) and Organization B (28-day limit), their sessions will expire after seven days. This is because a single session is used across all their organizations, so the most restrictive setting takes precedence. --- ## Consumer Terms of Service Updates | Claude Help Center Source: https://support.claude.com/en/articles/9264813-consumer-terms-of-service-updates Path: 22-Safety-Policy/consumer-terms-of-service-updates.md # Consumer Terms of Service Updates March 16, 2026 This support article covers the changes to our [Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms) that take effect **May 1, 2024.** At Anthropic, we review our policies and terms to ensure we’re providing the highest level of protection and clarity for our users. We encourage you to read our updated [Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms) in full, but at a high level, our latest updates provide clarity about how you can pay for and manage your subscription to our consumer services (like Claude Pro), if you purchased your subscription via an app. In case you haven't heard, Claude is now available as an iOS app via the [Apple App Store](), putting the power of AI right in your pocket! And for businesses looking to supercharge their productivity, the new [Team plan](../15-Claude-AI-Features/product-overview.md) helps you collaborate with Claude like never before. --- ## Cost and Usage Reporting in the Claude Console | Claude Help Center Source: https://support.claude.com/en/articles/9534590-cost-and-usage-reporting-in-the-claude-console Path: 22-Safety-Policy/cost-and-usage-reporting-in-the-claude-console.md # Cost and Usage Reporting in the Claude Console March 16, 2026 **Note:** Usage and Cost reporting is visible to the following user roles: **Developer, Billing, and Admin**. See [Claude Console Roles and Permissions](../13-Enterprise-Admin/claude-console-roles-and-permissions.md) for more information. The Claude Console provides detailed cost and usage reporting to help you effectively manage your API usage and associated costs. This guide walks you through these features and how to use them. ## Accessing Cost and Usage Reports Users with access to these reports can click into them on the left navigation menu on the Console: ------------------------------------------------------------------------ ## Usage Reporting The [Usage page](../04-API-Reference/Other/usage-limits.md) offers a detailed breakdown of your API usage across different models and API keys. ### Key Features - **Detailed Breakdown**: View usage data by model, date/time, and API key. Click into the bars on the bar chart for hour and minute granularity. - **Flexible Filtering**: Use selectors to choose specific models, months, or API keys - **Visual Representation**: A chart with input and output token counts. - **Usage Statistics**: See total input and output tokens for your selected filters. - **Rate-Limited Requests:** Review your requests that were blocked due to hitting rate limits. - **Rate Limit Use:** Visualizations of input and output tokens per minute compared with the overall ITPM or OTPM rate limit. - **CSV Export**: Download your usage data for further analysis or reporting. ### How to Use 1. Select the Workspace you want to view (or choose "All Workspaces"). 2. Select the model you want to view (or choose "All Models"). 3. Choose the month you're interested in (or narrow to a specific month/day). 4. Select an API key (or view data for all keys). 5. The chart and statistics will update based on your selections. 6. Use the export button to download a CSV of the displayed data. ### Rate Limit Use The Usage page also includes a separate section displaying rate limit use per-model for input and output tokens. You can click the dropdown in the upper left corner of this section to change the model and view related rate limit metrics. These visualizations can be used to determine when you’re hitting peak use for your organization, which specific rate limits need to be increased, and how you can increase your caching rate. **Rate Limit Use + Caching - Input Tokens:** This chart displays the hourly maximum number of uncached input tokens per minute (ITPM) alongside your cache rate (i.e. the percentage of input tokens read from the cache) and your current ITPM rate limit. **Rate Limit Use - Output Tokens:** This chart displays the hourly maximum number of output tokens per minute (OTPM) alongside your current OTPM rate limit. ------------------------------------------------------------------------ ## Cost Reporting The [Cost page](../04-API-Reference/Other/usage-limits.md) helps you understand your spending across different models. ### Key Features - **Model-Specific Data**: View costs for individual models or all models combined. - **Monthly Breakdown**: See costs for specific months. - **Daily Cost Chart**: Visualize your spending over time. - **Total Cost Statistics**: Get an overview of your total spending for the selected period, including web search and code execution costs. - **CSV Export**: Download cost data for your records for further analysis. ### How to Use 1. Choose the Workspace you want to view costs for (or select "All Workspaces"). 2. Choose the model you want to view costs for (or select "All Models"). 3. Select the month you're interested in. 4. You can see the chart, token cost, and tool use costs, which will update based on your selections. 5. Use the export button to download a CSV of the cost data. **Note**: Currently, it's not possible to break down usage or cost by individual users. --- ## Crisis Helpline Support in Claude | Claude Help Center Source: https://support.claude.com/en/articles/13171706-crisis-helpline-support-in-claude Path: 22-Safety-Policy/crisis-helpline-support-in-claude.md # Crisis Helpline Support in Claude March 16, 2026 *For medical emergencies, active injuries, or situations where you're in immediate physical danger, please contact emergency services (such as 911 in the US and Canada, or 112 in much of Europe) or go to your nearest emergency room.* *This guidance was developed in partnership with ThroughLine.* Claude may sometimes display crisis support resources in a banner or in its responses. These resources are designed to connect you with people who specialize in helping during difficult moments. ## Why am I seeing a crisis support message? Claude may show a banner with connections to crisis support resources when your conversation touches on topics that may be related to emotional distress, suicidal thoughts, or self-harm. This banner is surfaced by a separate detection system, not from Claude directly. These resources are there to make it easier to get help if you want it. You decide whether to use these resources, and there are no consequences for your account based on your decision to access resources. If the banner doesn't feel relevant to your situation, that's completely okay - you can simply dismiss it. We'd rather offer support when it's not needed than miss an opportunity to help someone who could use it. After you see the banner, it won't appear again for about two hours, but you can always access crisis resources at [claude.findahelpline.com](http://claude.findahelpline.com) anytime. ## What is a crisis helpline? Crisis helplines are free services staffed by trained personnel (who could be a volunteer, a counselor, or an individual who has been through similar situations) who provide support during tough times. You can usually reach them through multiple options (often phone, text, and/or online chat). Most operate around the clock, every day of the year, so help is available whenever you need it. ### What helplines offer - **A caring ear:** Responders are there to hear what you're experiencing, without judgment or criticism. - **Safety support:** If you're having thoughts of suicide or self-harm, they can work with you to create a plan for staying safe. - **In-the-moment guidance:** They can help you work through overwhelming feelings and figure out next steps. - **Connections to ongoing care:** They can point you toward community resources, support groups, or mental health services if you're looking for longer-term help. - **Support for concerned loved ones:** If you’re worried about a friend or family member, helplines can help you think through how to be there for them. You don't need to be at a breaking point to reach out. People contact helplines for all kinds of reasons - sometimes just to have someone listen. ## How to connect with a helpline Contacting a helpline is straightforward, and there's no special preparation needed: - **Choose your method:** Many helplines let you call, text, or chat online. You can check what's available and pick whichever feels most comfortable for you. - **Speak freely:** Share what's on your mind however it comes out. There's no script to follow. Something like "I'm not sure where to start" works perfectly fine. - **Feel free to let them guide the conversation:** The helpline responder will ask some questions to understand your situation and how they can best support you. You're always in control of what you share and where the conversation goes. - **Share only what you're comfortable with:** You can remain anonymous. There’s no requirement to provide your name or any identifying details. ### A few things to keep in mind - Crisis helplines provide immediate support, not ongoing therapy. However, they can help connect you with longer-term resources. - For medical emergencies, active injuries, or situations where you're in immediate physical danger, please contact emergency services (911 in the US or Canada and 112 in much of Europe) or go to your nearest emergency room. ## Understanding who provides what **Crisis helplines and Anthropic are entirely different organizations with different roles.** This distinction matters because it affects what kind of help you can get from each. It’s important to note that: - **Helpline responders are not Anthropic employees.** They specialize in emotional and mental health support. Questions about Claude, your account, technical issues, or billing aren't something they can address. - **Your Claude activity stays private.** Anthropic doesn't send your conversations to helplines. Helplines have no information about what you've discussed with Claude or any details about your account. ## Need help with Claude itself? For anything related to Claude or your Anthropic account, here's where to go: - **Support center:** Visit [support.anthropic.com](https://support.anthropic.com) - **Account questions:** Check your account settings for help options - **Feedback on responses:** The thumbs down button on any Claude response lets you flag concerns ## Frequently asked questions We worked with ThroughLine to provide answers to common questions about using a crisis helpline. ### Is there a cost for using crisis helplines via ThroughLine? Crisis helplines don't charge anything. Standard phone or texting rates from your carrier may apply, but the service itself is free. ### Where can I find a helpline? If you're in the United States, the 988 Suicide & Crisis Lifeline is available by call or text. For other countries, a directory of services worldwide maintained by ThroughLine can be found at [claude.findahelpline.com](http://claude.findahelpline.com). ### Does talking to a helpline actually make a difference? Studies consistently show that crisis counseling reduces distress and helps people feel more grounded. Responders are specifically trained to help during difficult moments, including supporting people through thoughts of self-harm. ### I'm not in a crisis. Is it still okay to call? Absolutely. Many people reach out when they're stressed, lonely, or just having a hard day. You don't need to meet some threshold of "bad enough" to deserve support. ### Can I call about someone else I'm worried about? Yes. Helplines support people who are concerned about others too. They can offer guidance on how to approach the situation and be helpful to the person you care about. ### Are there options besides phone calls? Many helplines offer text and online chat alongside traditional phone support. You can use whatever channel feels most comfortable to you. ### Will the helpline contact my family or anyone else? Generally, no. Conversations with support personnel are kept confidential. The main exception is if a responder believes there's an immediate, serious safety risk - and even then, they'll typically try to work with you first. Different helplines have slightly different policies, so feel free to ask when you connect. ### What about non-English speakers or people outside the United States? Helplines exist in countries around the globe, many offering support in local languages. You can locate services in your region on [claude.findahelpline.com](http://claude.findahelpline.com). ### Is it okay to contact a helpline multiple times? Yes, though some services have guidelines around frequency. Feel free to ask about their approach when you're connected. ### Does Anthropic send my Claude conversations to helplines? No. Your interactions with Claude remain with Anthropic. Helpline personnel have no access to your messages, account information, or anything else related to your use of Claude. When you contact a helpline, that's a completely separate conversation. ### What if I have to wait to speak with someone? High demand sometimes means wait times. If that happens, you can stay on the line, try reaching out via a different method (chat instead of phone, for instance), or contact an alternative helpline. [claude.findahelpline.com](http://claude.findahelpline.com) lists multiple options for most locations. ### I feel nervous about reaching out. That's a common feeling. Helplines understand this and won't push you to share more than you're ready to. You control the pace and depth of the conversation. If it helps, you might start with something simple: "I'm feeling nervous about this call." ### How are the crisis resources in Claude selected? We work with ThroughLine, an organization that curates and maintains a global directory of verified crisis helplines. The resources shown are selected based on your location to provide relevant, local support options. --- ## CSAM Detection and Reporting | Claude Help Center Source: https://support.claude.com/en/articles/9020328-csam-detection-and-reporting Path: 22-Safety-Policy/csam-detection-and-reporting.md # CSAM Detection and Reporting March 16, 2026 Anthropic strictly prohibits Child Sexual Abuse Material (CSAM) on our services. We are committed to combatting CSAM distribution across our products and will report flagged media and related information to the National Center for Missing and Exploited Children (NCMEC). As just one example of how we are combatting CSAM distribution: on our first-party services, we use a hash-matching tool to detect and report known CSAM that is included in a user or organization’s inputs. This tool provides access to NCMEC’s database of known CSAM hash values. When an image is sent in an input to our services, we will calculate a perceptual hash of the image. This hash will be automatically compared against the database. In the case of a match, we will notify and provide NCMEC information about the input and the related Account. As part of Anthropic’s safety process, we will also send a notice to the user or organization any time we report CSAM to NCMEC. If you receive a notification from us about CSAM detection and believe we’ve made an error, please email [\[email protected\]](https://support.claude.com/cdn-cgi/l/email-protection#aedbddcbdcddcfc8cbdad7eecfc0dac6dcc1dec7cd80cdc1c3). --- ## Exceptions to our Usage Policy | Claude Help Center Source: https://support.claude.com/en/articles/9528712-exceptions-to-our-usage-policy Path: 22-Safety-Policy/exceptions-to-our-usage-policy.md # Exceptions to our Usage Policy March 16, 2026 Anthropic maintains a comprehensive Usage Policy to ensure the responsible deployment of our AI systems. Anthropic may enter into contracts with government customers that tailor use restrictions to that customer’s public mission and legal authorities if, in Anthropic’s judgment, the contractual use restrictions and applicable safeguards are adequate to mitigate the potential harms addressed by this Usage Policy. For example, with carefully selected government entities, we may allow foreign intelligence analysis in accordance with applicable law. All other use restrictions in our Usage Policy, including those prohibiting use for disinformation campaigns, the design or use of weapons, censorship, domestic surveillance, and malicious cyber operations, remain. At this time, this policy only applies to models that are at AI Safety Level 2 (ASL-2) under our Responsible Scaling Policy (RSP). **What government entities are eligible for Usage Policy modifications?** Our evaluation of whether to tailor use restrictions to the mission and legal authorities of a government entity aims to balance enabling beneficial uses of our products and services with mitigating potential harms, and includes: - Our assessment of the models’ suitability for the proposed use cases. - The legal authorities of the agency in question. - The extent of the agency's willingness to engage in ongoing dialogue with Anthropic. - The safeguards in place to prevent misuse and mitigate risks of mistakes. - The degree of independent and democratic oversight of the organizations and their uses of AI technologies, including legislative or regulatory constraints and other relevant public commitments. --- ## Export your Claude data | Claude Help Center Source: https://support.claude.com/en/articles/9450526 Path: 22-Safety-Policy/export-your-claude-data-claude-help-center.md # Export your Claude data July 8, 2026 Data exports are available to individual Claude users on Free, Pro, and Max plans. Data exports include conversation data and the user data for your account. If you're a member of a Team or Enterprise plan, only your organization's Primary Owner can access data exports. For more information, see **[Export your organization's data](../13-Enterprise-Admin/how-can-i-export-my-organization-s-data.md)**. Individual Claude users can export user information and chat history from **[Settings \> Privacy](https://claude.ai/settings/data-privacy-controls)** on the web app or Claude Desktop (it's not possible to run an export from Claude for iOS or Android). Follow these steps to export your data: 1. Click on your initials in the lower left corner of your account. 2. Select "Settings" from the menu. 3. Navigate to the "Privacy" section. 4. Click the "Export data" button. Once the export has been processed, you will receive a download link via email. Please note: - There may be a small delay while the export is generated. - The email will be sent to the address associated with your account. - You must be signed in to your account to download your data using this link. - The download link will expire 24 hours after delivery. - If your link expires, you can always request a new one by repeating the export process. ## Can I import or migrate this data to another Claude account? Exported data can't be imported into another personal Claude account, and we don't support migrating data between personal accounts. If you're joining a Team or Enterprise organization, you don't need an export to bring your work with you—you can migrate your personal account directly into the organization's workspace. For details, see **[Move your personal Claude account to a Team or Enterprise organization](../21-Account-Support/can-individuals-with-pro-or-max-plan-accounts-migrate-them-to-team-or-enterprise-plan.md)**. --- ## Project Glasswing: Securing Critical Software for the AI Era Source: https://www.anthropic.com/glasswing Path: 22-Safety-Policy/glasswing.md # Project Glasswing: Securing Critical Software for the AI Era Project Glasswing is Anthropic's cross-industry initiative to secure the world's most critical software, powered by Claude Mythos Preview — Anthropic's most capable AI model for cybersecurity tasks. Announced on April 7, 2026. ## Overview Project Glasswing partners the organizations responsible for infrastructure that billions of people depend on with Claude Mythos Preview, giving their defenders a head start in the coming AI-driven era of cybersecurity. Anthropic is not making Claude Mythos Preview generally available due to its cybersecurity capabilities. Instead, access is restricted to vetted partners who build or maintain critical software infrastructure. ## Launch Partners The initiative brings together the following organizations as launch partners: - Amazon Web Services (AWS) - Anthropic - Apple - Broadcom - Cisco - CrowdStrike - Google - JPMorganChase - Linux Foundation - Microsoft - NVIDIA - Palo Alto Networks Anthropic has also extended access to a group of over 40 additional organizations that build or maintain critical software infrastructure. ## Financial Commitment - **$100M** in Claude Mythos Preview usage credits committed across Project Glasswing participants throughout the research preview - **$4M** in direct donations to open-source security organizations: - $2.5M to Alpha-Omega and the Open Source Security Foundation through the Linux Foundation - $1.5M to the Apache Software Foundation ## Claude Mythos Preview Claude Mythos Preview is a new general-purpose language model that sits in a fourth model tier named **Copybara**. Anthropic describes it as superior to any other existing AI frontier model. ### Capabilities - Capable of identifying and exploiting zero-day vulnerabilities in every major operating system and every major web browser - Has autonomously discovered thousands of zero-day vulnerabilities during testing - Can chain together 3, 4, or sometimes 5 vulnerabilities in sequence to produce sophisticated exploits - Demonstrates "a level of coding capability where [it] can surpass all but the most skilled humans at finding and exploiting software vulnerabilities" ### Benchmarks | Benchmark | Score | |-----------|-------| | SWE-bench Verified | 93.9% | | GPQA Diamond | 94.6% | | CyberGym | 83.1% | Highest-scoring model on record across all three benchmarks. ### Availability - **Not publicly available** — restricted to Project Glasswing partners and vetted organizations - Available through the Claude API, Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry for participants - Pricing described as "very expensive" but specific per-token pricing not publicly disclosed ## Why Limited Access As Newton Cheng, Frontier Red Team Cyber Lead at Anthropic, explained: Anthropic is not making the model generally available due to concerns that it may pose unprecedented cybersecurity risks and could increase the likelihood of large-scale AI-driven cyberattacks. The restricted access is designed to give defenders a head start before the capabilities become more widely available. ## See Also - [red.anthropic.com](red-home.md) — Anthropic's cybersecurity research site - [Claude Mythos Preview](../19-Reference/2026-mythos-preview.md) — Technical details - [Building AI for cyber defenders](https://www.anthropic.com/19-Reference/building-ai-for-cyber-defenders-anthropic.md) --- ## Holiday 2025 Usage Promotion | Anthropic Help Center Source: https://support.claude.com/en/articles/13163666-holiday-2025-usage-promotion Path: 22-Safety-Policy/holiday-2025-usage-promotion.md # Holiday 2025 Usage Promotion March 16, 2026 We’re giving Pro and Max subscribers a holiday gift—2x usage limits from December 25 through December 31. During this period, your plan’s usage limits will be doubled, giving you more room to explore Claude’s capabilities as you plan for the new year. ## Who is eligible? To be eligible for this promotion, you must meet the following criteria: - You have an active Pro, Max 5x, or Max 20x subscription. - You are an individual subscriber (this promotion does not apply to Team or Enterprise plans). - Both existing subscribers and new users who sign up for Pro or Max during the promotional period are eligible. ## What’s included in this promotion? During the promotional period, you’ll receive: - A 2x increase to your five-hour usage limits. - A 2x increase to your weekly usage caps. All weekly caps will be reset at the start of the promotional period (December 25 at 12:00 AM UTC). This promotion applies to usage on [claude.ai](http://claude.ai), Claude Code, and Claude in Chrome. ## When does this promotion run? This is a one-week holiday promotion running from Wednesday, December 25, 2025 at 12:00 AM UTC through Wednesday, December 31 at 11:59 PM UTC. ## What happens after the promotional period ends? After the promotional period ends, your usage limits will return to their standard levels based on your subscription plan. There is no additional charge—you’ll simply continue using Claude as part of your existing subscription. ## Terms and Conditions Additional usage is available from December 25, 2025 at 12:00 AM UTC through December 31, 2025 at 11:59 PM UTC. The increased usage limits apply to the Claude web app, Claude Code, and Claude in Chrome only. This promotion cannot be combined with other offers or promotions. Available to individual Pro, Max 5x, and Max 20x subscribers only. Team and Enterprise plans are not eligible. --- ## How can I create and manage projects? | Claude Help Center Source: https://support.claude.com/en/articles/9519177-how-can-i-create-and-manage-projects Path: 22-Safety-Policy/how-can-i-create-and-manage-projects.md # How can I create and manage projects? Projects are available to all users, including those with free Claude accounts. Free users can create a maximum of five projects. ## How to create a project 1. Hover over the left side of your account and click “Projects,” or navigate directly to this section: **[claude.ai/projects](https://claude.ai/projects)**. 2. Click "+ New Project" in the upper right corner. 3. Give your project a name and description (note that Claude will not have access to these details). 4. If you are on a Team or Enterprise plan, choose the visibility settings: - **Keep it private:** Only you and members you invite can view or use this project. - **Share with your broader organization:** Everyone in your organization can view and use this project (where enabled by administrators). Once your project is set up, you can initiate chats with Claude within the project. ## Add content to project knowledge You'll find the project knowledge base on the right side of your project's main page. Anything you upload to this space will be used across all of your chats within that project. ### Add content to your project knowledge base 1. Click on the "+" button to add content to the project. 2. Upload relevant documents, text files, or code snippets. 3. Claude will process this information and use it as context in your chats within the project. 4. If you are using a paid Claude plan, when your project knowledge approaches the context window limit, **[Claude will automatically enable RAG mode to expand your project's capacity](../15-Claude-AI-Features/retrieval-augmented-generation-rag-for-projects.md)**. ### Add project instructions to your project knowledge base 1. Click on "Set project instructions." 2. Add instructions for how you'd like Claude to behave and respond and click "Save instructions." 3. Claude will use these instructions for all the chats within the project. **Note:** Context is not shared across chats within a project unless the information is added into the project knowledge base. ------------------------------------------------------------------------ ## Share projects If you're on a Team or Enterprise plan, you can share projects with other users in your organization, unless your admin has turned off project sharing. See **[If you can't share projects](https://support.claude.com/en/articles/9519189-manage-project-visibility-and-sharing#h_d5a68ef397)** for what to expect. ### To share a project 1. Open the project you want to share. 2. Click the "Share project" button to the right of the project name. 3. Add individual members using their name or email address, or copy and paste a list of email addresses for bulk sharing. 4. Select the appropriate permission level for each member: - **Can view:** Members can see project contents, knowledge, and instructions, and chat within the project, but cannot edit it. - **Can edit:** Members can modify project instructions and knowledge, update member settings, and actively contribute to the project. 5. Click "Share" to send invitations. ### Manage shared project access - **To change permissions:** Open the sharing menu and select a new role for the member. - **To view who has access:** The sharing menu shows all current members and their permission levels. - **To remove access:** The project creator can click on the member's current role and select "Remove access." ### Find shared projects Your **[Projects page](https://claude.ai/projects)** has three tabs: "Your projects," "Organization," and "Shared with you." "Your projects" lists the projects you created, and "Organization" lists projects that other members have shared with your organization. If you can't find a project, check all three tabs. ------------------------------------------------------------------------ ## Star projects for quick access Starring a project allows for quick access from your projects and chats list, visible when hovering over the left side of your account. You can star a project from two different areas: ### From the “Projects” page 1. Locate the project on the “Projects” page. 2. Click on the three dots ("..." button) on the upper right corner of the project. 3. Select "Star" from the menu that appears. ### From the project 1. Open the relevant project. 2. Click on the star icon in the upper right corner. 3. The project will now appear in your starred items in the left side panel of your account. ------------------------------------------------------------------------ ## How to move chats into projects You can move a standalone chat into a project by clicking on the dropdown arrow next to the chat name, then “Add to project”: Browse or search for the correct project in the **Move chat** modal that appears, then click on it to move the chat. You can also remove chats from projects, or move them between projects, using the same dropdown menu within the chat: ------------------------------------------------------------------------ ## Move chats to manage Claude’s memory Memory is on by default for Free, Pro, and Max plans on the web, Claude Desktop, and Claude Mobile. On Team and Enterprise plans, memory is available when an owner has enabled it. For Team and Enterprise plans using Claude’s memory, the ability to move chats into and out of projects allows you to manage what’s included in Claude’s memory. Each project has its own memory, kept separate from your non-project chats. For example, if you accidentally start an unrelated chat in a project and need to remove it from the project-specific memory summary, you can click “Remove from project” so it will be included in Claude’s non-project memory instead. Refer to our article on chat search and memory for more information: **[What is Claude’s memory?](https://support.claude.com/en/articles/11817273-use-claude-s-chat-search-and-memory-to-build-on-previous-context#h_82126ebcc9)** ------------------------------------------------------------------------ ## How to archive projects Archiving is a way to organize your projects and declutter your project list. It's particularly useful for completed projects or those you're not actively working on but may need to reference in the future. **Important:** Archiving a project doesn't reset its sharing permissions or remove members. All members, permission levels, and project knowledge are preserved, and everything is restored exactly as it was when you unarchive the project. To revoke someone's access, remove them in the project's sharing settings. Here's what you need to know about archiving: - Archived projects will appear at the bottom of your main projects list. - You can still access conversations from archived projects. - There is no way to delete archived projects at this time (you must unarchive it first). ### To archive a project, follow these steps 1. Navigate to the project you want to archive. 2. Click on the three dots ("..." button) in the upper right corner. 3. Confirm that you want to archive the project. ### How to access archived projects You can access an archived project in the archived projects tab on the **[Projects page](https://claude.ai/projects)**. ## How to unarchive a project There are two ways to make archived project active again: ### From the archived projects tab 1. Locate the archived project. 2. Click on the three dots ("..." button) in the upper right corner. 3. Select "Unarchive" from the menu that appears. ### From the project 1. Navigate to the archived project. 2. Click on the three dots ("..." button) in the upper right corner. 3. Confirm that you want to unarchive the project. ------------------------------------------------------------------------ ## Delete projects **Note:** It's not possible to delete archived projects. To see the option to delete an archived project, you must unarchive it first. ### From the “Projects” page 1. Locate the project on the **[Projects page](https://claude.ai/projects)**. 2. Click on the three dots ("..." button) on the upper right corner of the project. 3. Select "Delete" from the menu that appears. 4. Confirm deletion in the pop-up by clicking "Yes, delete." ### From the project 1. Navigate to the project 2. Click on the three dots ("..." button) next to the star. 3. Select "Delete." 4. Confirm deletion in the pop-up by clicking "Yes, delete." --- ## How do I pay for my Claude API usage? | Claude Help Center Source: https://support.claude.com/en/articles/8977456-how-do-i-pay-for-my-claude-api-usage Path: 22-Safety-Policy/how-do-i-pay-for-my-claude-api-usage.md # How do I pay for my Claude API usage? August 19, 2026 This article explains how billing works for the Claude API, the playground, and Claude Code when you use them through a Claude Console account. Most organizations pay with prepaid usage credits. Organizations with an invoicing arrangement are billed monthly instead. ## Prepaid usage credits Claude API and playground usage is billed through prepaid usage credits. Buy credits before you use the API, and they're applied to your usage according to our current **[pricing](../17-Billing-Plans/pricing.md#api)**. Credits cover API access, playground usage, and Claude Code. You're billed only for successful API calls and completed tasks. Failed requests aren't charged. **Note:** If your client disconnects or times out in the middle of a request that was on track to succeed, that request is still charged. If you run out of credits, you can no longer call the API or use the playground until you add more. ## Buy credits 1. Log in to the Console with an Admin or Billing role. 2. Navigate to **[Settings \> Billing](../04-API-Reference/Other/usage-limits.md)**. 3. Click "Buy credits." 4. Enter the amount of credits you want to purchase and confirm. Purchased credits are available immediately. Your organization's available credit balance and credit usage are shown on the same **Billing** page. ## Set up auto-reload Auto-reload purchases additional credits automatically when your balance falls below a threshold you set. 1. On the **Billing** page, click "Edit" in the **Auto-reload** section. 2. Toggle auto-reload on or off. 3. If auto-reload is on, set the minimum balance that triggers a purchase and the amount to reload to. ## Credit expiration and refunds Purchased credits are subject to our **[Credit Terms](https://www.anthropic.com/legal/credit-terms)**. Credits expire one year from the purchase date, and the expiration date can't be extended. Expired credits appear in your **Invoice history** on the Billing page. All credit purchases are non-refundable. Learn more about how credit usage relates to rate limits in the **[Claude API docs](../04-API-Reference/Endpoints/rate-limits.md)**. ## Monthly invoicing Some organizations are billed monthly in arrears instead of buying credits upfront. This applies to Console organizations with an invoicing arrangement set up through our Sales team. On monthly invoicing, we aggregate your usage across API calls, Console usage, and any other services associated with your account, and bill it at our standard **[pay-as-you-go pricing](../17-Billing-Plans/pricing.md#api)**. At the end of each calendar month, you'll receive an invoice from Stripe. Enter your payment details in Stripe to pay it. You can view charges for the current billing period on the **[Billing](../04-API-Reference/Other/usage-limits.md)** page in your Console settings. If you need custom rate limits, monthly invoicing, or hands-on support, **[contact our Sales team](https://claude.com/contact-sales)**. ## Update your Console payment method 1. Log in to the Console with an Admin or Billing role. 2. Navigate to **[Settings \> Billing](../04-API-Reference/Other/usage-limits.md)**. 3. Click the pencil icon next to your current payment method. 4. Enter your new card details in the **Update payment method** modal, then click "Update." --- ## How up-to-date is Claude's training data? | Claude Help Center Source: https://support.claude.com/en/articles/8114494-how-up-to-date-is-claude-s-training-data Path: 22-Safety-Policy/how-up-to-date-is-claude-s-training-data.md # How up-to-date is Claude's training data? While we're constantly updating Claude's data, each model has a knowledge cutoff: - Claude Sonnet 5.5 was trained on data up until June 2026. - Claude Opus 5.5 was trained on data up until June 2026. - Claude Fable 5.1 was trained on data up until June 2026. - Claude Opus 5 was trained on data up until May 2026. - Claude Sonnet 5 was trained on data up until January 2026. - Claude Fable 5 was trained on data up until January 2026. - Claude Opus 4.8 was trained on data up until January 2026. - Claude Opus 4.7 was trained on data up until January 2026. - Claude Sonnet 4.6 was trained on data up until August 2025. - Claude Opus 4.6 was trained on data up until August 2025. - Claude Haiku 4.5 was trained on data up until July 2025. - Claude Opus 3 was trained on data up until August 2023. These models may not be aware of events or information that occurred after their respective cutoff dates. If you ask about more recent events, the model may not have accurate information. You can refer to **[Models overview](https://docs.claude.com/en/docs/about-claude/models/overview)** in our Claude Docs for more detailed information about our models. --- ## I think a user is infringing my copyright or other intellectual property. How do I report it? | Claude Help Center Source: https://support.claude.com/en/articles/10023646-i-think-a-user-is-infringing-my-copyright-or-other-intellectual-property-how-do-i-report-it Path: 22-Safety-Policy/i-think-a-user-is-infringing-my-copyright-or-other-intellectual-property-how-do-i-report.md # I think a user is infringing my copyright or other intellectual property. How do I report it? March 16, 2026 If you believe someone is infringing your intellectual property rights, you can send us notice of the infringement and we’ll take appropriate action, which may include suspension or termination of the accounts of repeat copyright infringers. Notices can be submitted through [this form](https://claude.com/form/anthropic-content-reporting) or by mail to the address below: Anthropic PBC 548 Market Street PMB 90375 San Francisco, CA 94104-5401 Attn: Legal / Copyright Agent Written claims concerning copyright infringement must contain the following information: - A physical or electronic signature of the person authorized to act on behalf of the owner of the copyright interest; - A description of the copyrighted work that you allege has been infringed upon; - A description of where the material that you alleged is infringing is located on the platform; - Your address, telephone number, and e-mail address; - A statement by you that you have a good-faith belief that the disputed use is not authorized by the copyright owner, its agent, or the law; and - A statement by you, made under penalty of perjury, that the above information in your notice is accurate and that you are the copyright owner or authorized to act on the copyright owner’s behalf. For questions, please email [\[email protected\]](https://support.claude.com/cdn-cgi/l/email-protection#b6d2dbd5d7f6d7d8c2dec4d9c6dfd598d5d9db) or call (415) 326-6303. --- ## I’ve been using other large language models (LLMs) to power my product. How should I alter my prompts when switching to Claude? | Claude Help Center Source: https://support.claude.com/en/articles/8114533-i-ve-been-using-other-large-language-models-llms-to-power-my-product-how-should-i-alter-my-prompts-when-switching-to-claude Path: 22-Safety-Policy/i-ve-been-using-other-large-language-models-llms-to-power-my-product-how-should-i-alter.md # I’ve been using other large language models (LLMs) to power my product. How should I alter my prompts when switching to Claude? March 16, 2026 You can use the prompt improver in the Claude Console to automatically adapt prompts that were originally written for other AI models. --- ## Law Enforcement Requests | Claude Help Center Source: https://support.claude.com/en/articles/9035075-law-enforcement-requests Path: 22-Safety-Policy/law-enforcement-requests.md # Law Enforcement Requests March 16, 2026 Anthropic PBC discloses account records solely in accordance with our Terms of Service and applicable law. For more information about Anthropic’s policies for handling governmental requests for user information, see [here](what-is-anthropic-s-policy-for-handling-governmental-requests-for-user-information.md). If you are a law enforcement agent who is authorized to gather evidence in connection with an official investigation, you may request records from Anthropic by emailing [\[email protected\]](https://support.claude.com/cdn-cgi/l/email-protection#b4d8d5c399d1dad2dbc6d7d1d9d1dac099c6d1c5c1d1c7c0c7f4d5dac0dcc6dbc4ddd79ad7dbd9). Please include the following information with your request: - Law Enforcement Agency Country - City - State/Province - Zip/Postal Code - Law Enforcement Address - Name of Court/Policy Department/Authority/Agency - Name of Contact Person Handling this Matter (Detective, Investigator, etc.) - Official Law Enforcement Agency Request Email Address - Contact Person’s Phone Number - Description of legal Inquiry - Matter Type of legal Inquiry - Attach Any Relevant Documentation (e.g., Subpoena, Warrant) - NCMEC Report Identifier (If Applicable) --- ## Manage plugins for your organization | Claude Help Center Source: https://support.claude.com/en/articles/13837433-manage-cowork-plugins-for-your-organization Path: 22-Safety-Policy/manage-claude-cowork-plugins-for-your-organization.md # Manage plugins for your organization Plugin marketplaces let Team and Enterprise plan owners distribute curated plugins to everyone in their organization. You create a marketplace, add plugins to it, and control exactly which plugins your team members can see and use. Plugins you distribute appear in chat (on the web and the Chat tab in Claude Desktop), in Claude Cowork, and in Claude Code sessions where members sign in with the same Claude account. Owners and Primary Owners of Team and Enterprise plans can manage organization plugins in **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)**. On Enterprise plans, members with a custom role that includes managing the organization's libraries can too. **Requirements:** Cowork and Skills must both be enabled for your organization before you can use plugin marketplaces. For a reference version of these controls, see **[Manage plugins for your organization](../08-Plugins-Skills/plugins-org.md)** in the Claude Code docs. **Note:** Turning off Skills for your organization also stops skills and plugins from syncing to Claude Code, and removes the ones that already synced there. Turning off Cowork doesn't affect the sync to Claude Code. To keep skills and plugins in Claude but stop only the sync, set `syncClaudeAiSkills` and `syncClaudeAiPlugins` to `false` in Claude Code managed settings. Learn more about **[Claude Code admin setup](../01-Getting-Started/setup.md#advanced-setup)**. **Note:** Marketplaces are how owners distribute plugins to their organization. Users can also share a plugin they built with specific colleagues or groups, or submit it to be published to your organization's library. Sharing and publishing are controlled by the settings in **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** in the “Policy” tab, and plugin submissions are reviewed there on the "Requests" tab. Learn more about **[using plugins in Claude](https://support.claude.com/en/articles/13837440-use-plugins-in-claude)** and **[letting users publish skills and plugins to your organization](https://support.claude.com/en/articles/13119606-provision-and-manage-skills-for-your-organization#h_1abc45a27c)**[.](https://support.claude.com/en/articles/13119606-provision-and-manage-skills-for-your-organization#h_1abc45a27c) ------------------------------------------------------------------------ ## See what's in your organization The “Inventory” tab lists every skill and plugin your organization governs, including the ones users created for themselves. Skills and plugins now live on the same page, so you don't need to switch between settings. For each item, the table shows its source, version, capabilities, audience, and how many people used it in the last 30 days. To find an item, search by name or use the filters: - **Source:** Your organization, Organization library, or a specific marketplace - **Audience:** Who can use the item - **Type:** Skills or plugins Skills your organization manages appear under **Organization library**. You manage plugin marketplaces in the **Marketplaces** tab. To act on an item, click the menu button at the end of its row. You can view details and files, see version history, and change default and group access. For skills and plugins that users created, the Inventory tab shows metadata and sharing status. It doesn't show the files themselves. ## Use Anthropic-built marketplaces Anthropic provides built-in marketplaces of plugins for different functions, such as legal and finance. A Knowledge Work marketplace is added to your organization by default. To add an Anthropic-built marketplace: 1. Go to **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** and click the “Marketplaces” tab. 2. Click “Add,” then select “Add marketplace.” 3. Select "Browse Anthropic sources." 4. Click "Add" on each one you want to appear for everyone in your organization. To remove the Knowledge Work marketplace if it isn't relevant to your teams: 1. Go to **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** and click the “Marketplaces” tab. 2. Find **Knowledge Work**. 3. Click the menu button in the upper right corner. 4. Select "Remove." Anthropic-built marketplaces show readable names, like "Knowledge Work," instead of the underlying repository slug. ------------------------------------------------------------------------ ## Create your own marketplace Beyond the Anthropic-built marketplaces, you can create your own. There are two ways to add plugins to a marketplace you create: - **Manual upload:** Upload individual plugin ZIP files through the admin UI. Best for quick iteration, one-off tools, or teams that don't keep plugins in a Git repository. - **Repository syncing:** Connect a private GitHub or GitLab repository and Claude syncs plugins from it. Best when multiple developers collaborate on plugins or you want version-controlled updates. You can use both approaches in parallel. For example, run a GitHub-synced marketplace for your core plugins and a separate manual marketplace for ad-hoc tools. ### Set up a manual marketplace 1. Go to [](https://claude.ai/admin-settings/plugins) **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)**. 2. Click “Add,” then select “Upload a plugin.” 3. If this is your first time setting up a marketplace, "Upload to a new marketplace" is auto-selected. You'll be able to choose "Add to an existing marketplace" when uploading plugins later. 4. Enter a name for your marketplace. 5. Either drag your files in, or click the upload prompt and select your file. The file must be a valid .zip under 200 MB. 6. Repeat for each plugin you want to add. 7. Click "Upload" to add your plugins to a new marketplace. If you upload a plugin with the same name as an existing one, it overwrites the previous version automatically. You don't need to delete the old one first. ### Set up a GitHub-synced marketplace **Prepare your repository** You can connect a repo hosted on github.com or on your organization's GitHub Enterprise host. On github.com, your repository must be **private or internal**—public repos aren't allowed for organization marketplaces. To sync from GitLab, see **[Set up a GitLab-synced marketplace](#h_6be3dfbfbc)**. A plugin source can be private in three cases: - A github.com source that shares your marketplace repository's owner, which organization sync fetches through the Claude GitHub App. - A source on your organization's GitHub Enterprise host with your organization's GitHub Enterprise App installed on that repository. - A url or git-subdir source on the same GitLab host as your marketplace repository. On gitlab.com, the source must also be under the same top-level group or user namespace as the marketplace repository. Every other source is fetched without credentials, so it must be a public repository on github.com, gitlab.com, or bitbucket.org. Sources on any other host are rejected. If your plugin code lives in a private repository that doesn't meet the criteria above, copy those plugin folders into the marketplace repository and change each plugin's source to a relative path (a git subtree or a CI step that vendors the files works well). For details on plugin structure and formatting, see the **[plugin manifest reference](../08-Plugins-Skills/plugins-reference.md)**. Additional resources: - **[Create a marketplace](../08-Plugins-Skills/plugin-marketplaces.md)** - **[Create a plugin](../08-Plugins-Skills/plugins-create.md)** - **[Creating a new GitHub repository](https://docs.github.com/en/repositories/creating-and-managing-repositories/creating-a-new-repository)** **Connect the repository** 1. Make sure both Cowork and Skills are enabled for your organization. 1. **[Enable Cowork](../17-Billing-Plans/use-claude-cowork-on-team-and-enterprise-plans.md#h_71cdc52dfc)** 2. **[Enable Skills](https://support.claude.com/en/articles/13119606-provision-and-manage-skills-for-your-organization#h_7673241237)** 2. Go to **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** and click the “Marketplaces” tab. 3. Click “Add plugins,” then select “Sync from GitHub.” 4. Enter the repository in `owner/repo` format (for example, `acme-corp/claude-plugins`). Your personal GitHub token is verified to confirm you have access, then Cowork uses its GitHub App installation token for sync operations. **Can't see your repo?** Make sure the Claude GitHub App is installed in that repository. **How syncing works** An initial sync runs automatically when you connect a repository. In the GitHub creation flow, you can also turn off "Sync automatically," which is on by default. With it on, a sync runs when a pull request is merged into the branch the marketplace follows, or when someone pushes to that branch directly. The person turning automatic sync on or off must have admin-level access to that repository on GitHub. This is checked through their personal GitHub connection, which is separate from the Claude GitHub App installation. Without admin access, the page shows "Cannot access repository. Ensure the repository exists and the Claude GitHub App is installed," even when the App is installed correctly and manual updates work. The Claude GitHub App's **Webhooks (Read & Write)** permission must also be approved on the installation. On installations created before this permission was introduced, GitHub shows a "Claude is requesting updated permissions" prompt that a repository or organization admin needs to approve. Once enabled, automatic sync for a GitHub repository runs when a pull request that includes a plugin version bump is merged to the repository's default branch. Direct pushes to the default branch don't trigger a sync. You can always trigger a sync manually by clicking "Re-sync" on the marketplace. During a sync, Cowork compares the latest commit in your repo against the last-synced commit. If nothing has changed, the sync is skipped. If there are changes, Cowork reads the manifest, validates each plugin, and replaces all plugins in the marketplace with the current state of the repo. Syncs can take up to 30 minutes depending on the number of plugins. **Important:** If a sync fails, members keep the last synced version of each plugin. Check the failure message, fix the repo, and re-sync. ### Set up a GitLab-synced marketplace You can sync an organization marketplace from a repository on gitlab.com or on a self-managed GitLab instance. For supported plugin source types and which sources can be private, see **Prepare your repository** above. GitLab support is in beta and applies to plugin marketplace sync only. Claude Code on the web doesn't support GitLab repositories yet. **Before you start** - **Role.** You need the Owner or Primary Owner role to add a GitLab configuration. - **Project visibility.** On gitlab.com, the marketplace project must be private or internal. On a self-managed instance, any visibility works. - **Access token.** Create a GitLab access token for Claude to read the marketplace project and any plugin source projects on the same host. Personal, group, and project access tokens all work. The token's user needs at least the Reporter role on those projects. - Legacy (scoped) token: at least the `read_api` scope. - Fine-grained personal access token: the Project: Read, Branch: Read, and Repository: Read permissions. - Optional, for automatic webhook setup (step 3): the Maintainer role on the marketplace project plus the `api` scope (legacy) or the Webhook: Create and Delete permission (fine-grained). Without these, you add the webhook by hand once (step 4). - **Self-managed instances only.** - The instance's hostname must resolve to a public IP address, and the instance must accept HTTPS connections from **[Anthropic's outbound IP addresses](../04-API-Reference/Endpoints/ip-addresses.md#outbound-ip-addresses)**. - If a private certificate authority issued its TLS certificate, have the CA certificate (PEM) ready. - Webhook deliveries for automatic sync come from your instance to api.anthropic.com, so the instance must be able to make outbound HTTPS requests to that host. **Step 1: Add a GitLab configuration** To add a GitLab configuration: 1. Go to **[Organization settings \> Claude Code](https://claude.ai/admin-settings/claude-code)**. 2. Under **Self-hosted infrastructure**, find **GitLab** and click "Add configuration." 3. Enter a display name, the hostname (gitlab.com, or your instance's hostname such as gitlab.example.com), the access token, and, for a self-managed instance with a private CA, the CA certificate. 4. Click "Add configuration." Claude runs a connection test right away and shows the results in a **GitLab connection test** dialog. 5. (Optional) To check that the token can read your marketplace project, enter its path (for example, `platform/claude-plugins`) under **Project path** and click "Test sync access." You can re-run the test at any time from the configuration's menu with **Test connection**. The hostname can't be changed later. If it changes, delete the configuration and add a new one. **Step 2: Add the marketplace** To add the marketplace: 1. Go to **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** and click the "Marketplaces" tab. 2. Click "Add," then select "Sync from GitLab." 3. In **GitLab repository URL**, enter the project's HTTPS URL, for example [https://gitlab.example.com/platform/claude-plugins](https://gitlab.example.com/platform/claude-plugins). Projects in nested subgroups work. 4. Leave **Sync automatically** on if you want pushes to trigger a sync (see **Step 3**). 5. Choose the **Default access** for the plugins the marketplace contains. 6. Click "Create." Claude reads the project's default branch and validates the marketplace file before creating the marketplace, which is named after the project path. **Step 3: Automatic sync** With **Sync automatically** on, every push to the project's default branch triggers a sync through a webhook on the GitLab project. If your token can manage webhooks (see **Before you start**), Claude creates the webhook for you and there's nothing else to do. You can turn **Sync automatically** on or off later from the marketplace's menu. Turning it on sets up the webhook the same way. **Step 4: If Claude can't create the webhook** If the token can't manage webhooks, Claude shows a **Finish webhook setup in GitLab** message on screen with a **Webhook URL** and a token. The token is shown only once, so finish this step before closing the message. 1. In your GitLab project, open **Settings \> Webhooks** and add a new webhook with the URL from the message. 2. Paste the token into the field. 1. If the message shows a **Secret token**, paste it into GitLab's Secret token field. 2. If the message shows a **Signing token** (gitlab.com and self-managed versions 19.1 or later), select "Generate signing token" in GitLab and replace the generated value with the one from Claude. 3. Enable **Push events** and save. 4. (Optional) Use **Test \> Push events** on the new webhook in GitLab and confirm it reports HTTP 200. If you lose the token, open **Configure webhook** from the marketplace's menu, click "Remove webhook," then "Enable webhook" to get a new one. The old token will stop working. ### Choose between manual upload and repository sync [TABLE] ------------------------------------------------------------------------ ## Control plugin distribution Once your marketplace has plugins, you control how they're distributed using installation preferences. For each plugin, you can set one of four options: [TABLE] **Important:** Plugins set to "Installed by default" or "Required" also install in Claude Code for users who sign in with their Claude account. In Claude Code, the plugin's hooks, sub-agents, and MCP servers run on the user's computer, and a "Required" plugin can't be disabled there. Review a plugin's hooks before you set it to "Required." Learn more about **[synced plugins](../08-Plugins-Skills/plugins-reference.md#synced-plugins)** in the Claude Code docs. ### Set preferences 1. In **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)**, click the “Inventory” tab. 2. Find the plugin and click the menu button at the end of its row. 3. Click “Default access,” then select an option under **Install**. 4. Changes take effect on each member's next session or plugin refresh. ### What members experience Members browse available plugins on the **Discover** tab in **Customize \> Plugins**. Plugins you set to "Installed by default" or "Required" appear in their list automatically. Plugins you set to "Available to install" show up on **Discover** for members to add themselves. Members can't edit organization-managed plugins, which prevents conflicting changes to shared tooling. ------------------------------------------------------------------------ ## Customize plugin access by group Enterprise admins can override a plugin's organization-wide installation preference for specific groups. For example, you can auto-install a plugin for the Engineering group, make it available for Legal to install on their own, and hide it from everyone else. Group-level plugin access is available on Enterprise plans. You set it on the same **Organization settings \> Plugins & skills** page, which requires an Owner or a custom role that includes managing the organization's libraries. ### How group overrides work Each plugin in your marketplace has an organization-wide installation preference (Installed by default, Available to install, Required, or Not available). By default, every group inherits that organization-wide setting. When you set a group-level override for a plugin, it replaces the org-wide setting for members of that group. The resolution order is: group setting, then org-wide setting, then marketplace default. ### Set plugin access for a group 1. In [](https://claude.ai/admin-settings/plugins) **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)**[,](https://claude.ai/admin-settings/skills) click the “Inventory” tab. 2. Find the plugin you want to customize and click the menu button at the end of its row. 3. Click “Group access…”. 4. Click “Add groups” next to **Install targeting**. 5. Select the group and choose one of the installation preferences listed above. Both manually created groups and SCIM-provisioned groups from your identity provider appear in the group picker and work the same way. ### What happens when a member is in multiple groups If a member belongs to two or more groups with different settings for the same plugin, the **most permissive** setting applies. The order from most to least permissive is: Required \> Installed by default \> Available to install \> Not available. For example, if Group A sets a plugin to "Not available" and Group B sets it to "Installed by default," a member in both groups gets the plugin installed by default. **Note:** This differs from how group spend limits resolve. Spend limits apply either the higher or lower group value depending on your **Multi-group spend limit** setting. Plugin access applies the most permissive value, because groups here are meant to enable access for teams that need a tool, not to act as a security boundary. If you need to hard-block a plugin, set its org-wide preference to "Not available" and only grant access to the groups that should have it. ### What happens when a group is deleted If a group is removed (for example, deleted from your identity provider), the override remains in the admin UI but is flagged as orphaned. It has no effect on members (since no one belongs to a deleted group) and doesn't count toward the custom access badge. You can clear orphaned overrides from the plugin's “Group access…” settings. ### Do group settings persist across marketplace re-syncs? Yes. Group-level overrides persist when you re-sync a GitHub- or GitLab-connected marketplace. They're only removed if the plugin itself is deleted from the marketplace. ------------------------------------------------------------------------ ## Update and remove plugins ### Manual marketplaces To update a plugin, upload a new ZIP file with the same plugin name. The new version overwrites the existing one automatically. Plugin names are the unique identifier, so `legal` will always replace `legal`. To remove a plugin, delete it from your marketplace in **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** under the “Inventory” tab. ### GitHub-synced marketplaces Push your changes to the connected repository, then go to **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** and click the “Marketplaces” tab, find your marketplace, and click "Update" to trigger a sync. Each sync replaces all plugins with the current state of the repo. If an owner has enabled "Sync automatically" for the marketplace, a sync also runs whenever a pull request with a plugin version bump is merged to the repository's default branch. For GitLab-synced marketplaces, see **[Set up a GitLab-synced marketplace](#h_6be3dfbfbc)**. To remove a plugin, delete it from the repository and trigger a sync. ------------------------------------------------------------------------ ## Limits [TABLE] ------------------------------------------------------------------------ ## Naming rules Plugin names must use **lowercase words separated by hyphens** (for example, `deployment-tools`, not `Deployment Tools`). The following marketplace names are reserved and can't be used: - `claude-code-marketplace` - `claude-code-plugins` - `claude-plugins-official` - `anthropic-marketplace` - `anthropic-plugins` - `agent-skills` - `life-sciences` Names that impersonate official Anthropic marketplaces are also blocked. **Note:** Plugin authors can set a `displayName` so a plugin shows a readable name in the catalog instead of its slug. If an author doesn't set one, the plugin shows its slug (for example, `deployment-tools`). ------------------------------------------------------------------------ ## Troubleshooting ### Upload rejected Common causes: the file exceeds 200 MB, it isn't a valid ZIP file, or the marketplace has reached the 1000-plugin limit. Check the file size and format, and remove unused plugins if you're at capacity. If skill and plugin scanning is on, a plugin can also be rejected because it was flagged for malicious content. Review the reason, fix the issue, and upload the plugin again. ### Plugin not appearing for members Check the plugin's installation preference in your marketplace settings. If it's set to **Not available**, members won't see it. Also confirm that Cowork and Skills are both enabled for your organization. ### Updated plugin not reflecting for members Changes take effect on each member's next session or plugin refresh. In Claude Code, users get the change the next time they start Claude Code. If the update still isn't showing, confirm the upload succeeded by checking the plugin version in your marketplace. ### GitHub sync fails with a content error One or more plugins in your repo is likely formatted incorrectly. Fix the formatting issue, push the update to GitHub, and trigger the sync again. For plugin structure requirements, see the **[plugin manifest reference](../08-Plugins-Skills/plugins-reference.md)**. ### Sync fails with "External plugin source type is not supported. Supported types: git-subdir, github, url" or plugins are skipped with "Repository not found on gitlab.com. Check the URL and make sure the repository is public." One or more plugin entries in your `marketplace.json` use a `source` that points outside the connected repository (a `github`, `url`, or `git-subdir` source), and organization sync can't fetch it. A private source only works in three cases: a github.com repository shares your marketplace repository's owner, a repository on your organization's GitHub Enterprise host with your GitHub Enterprise App installed on it, or a url or git-subdir source on the same GitLab host as your marketplace repository (on gitlab.com, also under the same top-level group or user namespace). For any other private source, move the plugin folders into the marketplace repository and change each entry's `source` to a relative path (for example, `"./plugins/my-plugin"`), then push and re-sync. Alternatively, upload the affected plugins individually via **[Organization settings \> Plugins & skills](https://claude.ai/admin-settings/skills)** Click “Add,” “Upload a plugin,” then select "Add to an existing marketplace." Plugins uploaded through a member's own Customize menu are installed only for that member and aren't distributed to your organization, although members can share plugins with specific colleagues or groups if sharing is turned on. ### Can't see a GitHub repo when connecting Make sure the Claude GitHub App is installed in that repository. Your personal GitHub token is checked first to confirm access, but the sync itself uses the GitHub App installation token. ### "Cannot access repository" when turning on "Sync automatically" If manual updates work but turning on "Sync automatically" shows "Cannot access repository. Ensure the repository exists and the Claude GitHub App is installed," there are two likely causes: - **You don't have admin access to the repository.** Turning on automatic sync creates a webhook, which requires admin-level access to the repo through your personal GitHub connection. Ask a repository admin to enable the toggle, or have your GitHub access upgraded. - **The Claude GitHub App's Webhooks permission hasn't been approved.** On older installations, GitHub shows a "Claude is requesting updated permissions" prompt. A repository or organization admin needs to approve the **Webhooks (Read & Write)** permission on the installation. ### "No GitLab instance is configured for your organization yet. Add one under Claude Code settings, then come back here" when adding a marketplace If you see this message when adding a marketplace in GitLab, make sure you’ve added the GitLab configuration first. See **Step 1: Add a GitLab configuration** under **[Set up a GitLab-synced marketplace](#h_6be3dfbfbc)**. ### "This URL isn’t on a configured GitLab instance" Make sure the URL's hostname matches a configured GitLab hostname exactly. ### Adding a gitlab.com project fails with "Failed to create marketplace. Try again." Check that the project's visibility is private or internal. Public gitlab.com projects can't be used as organization marketplaces. ### The connection test fails at Reach host (for example "The hostname couldn’t be resolved," "The connection was refused," or "GitLab didn’t respond in time"), or adding a marketplace on a self-managed instance fails with a generic error Confirm the instance is reachable from the public internet over HTTPS and that Anthropic's outbound IP addresses are allowed through your firewall. "A secure connection couldn’t be established" usually means the CA certificate is missing or wrong. ### Errors that start with "Authentication to … failed" or "Access denied" The token is expired, revoked, or missing a scope or role listed in the **Before you start** section under **[Set up a GitLab-synced marketplace](#h_6be3dfbfbc)**. Create a new token and paste it into the configuration (**Edit \> Access token**). --- ## Manage Claude’s tool access | Claude Help Center Source: https://support.claude.com/en/articles/13730515-manage-claude-s-tool-access Path: 22-Safety-Policy/manage-claude-s-tool-access.md # Manage Claude’s tool access March 16, 2026 When you connect many services to Claude, you can control how those connectors are loaded into your conversations. This helps Claude work more accurately and efficiently, especially if you've added 10 or more connectors. Tool access modes are available for all users on Claude, Cowork, Claude Desktop, and Claude Mobile (iOS and Android). ## Why tool access matters Each connector takes up space in a conversation. With a small number of connected services, this is rarely noticeable. But as your connector library grows, the combined overhead can limit how much room is left for your actual work: documents, code, and conversation history. To address this, Claude supports three tool access modes that control when and how your connectors are loaded. ------------------------------------------------------------------------ ## Tool access modes You can manage Claude’s access to your connectors per conversation using the **Tool access** setting in your chat. Choose from three options: - **Auto** *(default)*: Claude decides dynamically which connectors to load based on what you're working on. This is the best starting point for most users. - **Always available**: All your connectors are loaded at the start of every conversation. Claude can use any of them immediately, without any extra steps. - Best for: Fewer than 10 connectors you use constantly. - Trade-off: Uses more conversation space upfront. - **On demand:** Connectors aren't loaded until Claude searches for the right one based on your request. Claude finds the most relevant connectors and loads only those. - Best for: Large connector libraries (10 or more), or when you're running into conversation length issues. - Trade-off: Claude may take an extra step to find the right connector before using it. ------------------------------------------------------------------------ ## Which mode should I use? [TABLE] ------------------------------------------------------------------------ ## How to change your tool access setting You can set your tool access mode per conversation by following these steps: 1. Open a chat with Claude. 2. Click the “+” button in the lower left corner of your chat, or type "/" to open the menu. 3. Mouse over “Connectors,” then “Tool access.” 4. Select your preferred mode from the three options. Your selection only applies to that conversation. You can change it at any time. ------------------------------------------------------------------------ ## Frequently asked questions ### Will “On demand” mode miss the connectors I need? Claude searches for the most relevant connectors based on your request, so it works well for most tasks. For connectors that need to be available every time, use “Always available” or set that connector's access individually. ### Why does Claude sometimes add an extra message to use a connector? In “On demand” mode, Claude searches for the right tool before using it. This search step adds one interaction, but keeps your conversation from hitting length limits when you have many tools connected. --- ## Manage user feedback settings on Claude Console | Claude Help Center Source: https://support.claude.com/en/articles/10504853-manage-user-feedback-settings-on-claude-console Path: 22-Safety-Policy/managing-user-feedback-settings-on-claude-console.md # Manage user feedback settings on Claude Console March 16, 2026 As an Admin of your Claude Console account, you can manage the ability for members of your organization to submit feedback to Anthropic via thumbs up / thumbs down. To manage feedback for your Console organization: 1. Navigate to [Settings \> Privacy controls](../04-API-Reference/Other/usage-limits.md). 2. Toggle the feedback switch on or off. More information on how Anthropic collects, uses, and stores feedback data can be found in our Privacy Center: [How long do you store my organization’s data?](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data) --- ## Model Safety Bug Bounty Program | Claude Help Center Source: https://support.claude.com/en/articles/12119250-model-safety-bug-bounty-program Path: 22-Safety-Policy/model-safety-bug-bounty-program.md # Model Safety Bug Bounty Program ## Purpose We believe external testing is crucial for building a safe AI ecosystem. As model capabilities advance, the consequences of jailbreaks could become increasingly significant. This ongoing Program builds on our successful previous bug bounty initiatives with several key objectives: 1. Identify universal jailbreaks in our deployed systems with ASL-3 protections 2. Provide continuous assessment of our safeguards' effectiveness 3. Test our monitoring systems' ability to detect vulnerabilities 4. Incentivize the user of one central legitimate channel for reporting publicly available jailbreaks ## Program Overview Our Model Safety Bug Bounty Program is run through HackerOne. Through this Program, we are interested in finding universal jailbreaks that surpass our [Constitutional Classifiers](../19-Reference/constitutional-classifiers.md) system. We also occasionally run targeted programs within our overall Program to test the robustness of classifiers we hope to launch in the future. A universal jailbreak is a generalized technique that reliably elicits policy-violating responses from a language model, regardless of the input prompt. Unlike narrow jailbreaks, which depend on the specifics of a particular question or context, universal jailbreaks work across a wide range of prompts and scenarios. This is an ongoing Program. Once accepted to the Program on HackerOne, participants can submit jailbreak reports at any time through this Program. **To help with your red-teaming efforts, we provide access to a free model alias that reflects the model and classifiers live on our latest, most advanced model**. **Your use of this free model alias must be limited to performing authorized red-teaming activities.** ## Program Scope This Program is primarily interested in discovering jailbreaks that are **universal**, in that they can reveal harmful information across a wide range of queries, and **detailed**, in that they reveal highly specific harmful information related to biological threats. To emphasize, we are interested in jailbreaks that extract information that answers a set of **harmful biological questions that we share with accepted participants in the Program.** We will pay **up to \$35,000 per novel, universal jailbreak identified.** We are only interested in jailbreaks that reveal substantial amounts of harmful information based on our sole criteria and discretion. We award bounties using a sliding scale based on an internal grading rubric which determines how detailed and accurate responses are. This program is scoped to jailbreaks on our Constitutional Classifiers. For technical vulnerabilities that potentially exist on our Information Systems such as misconfigurations, CSRFs or cross site request forgeries, privilege escalation attacks, SQL Injection, XSS, and directory traversal attacks, please refer to our [Responsible Disclosure Policy](https://www.anthropic.com/responsible-disclosure-policy) and submit your report [here](https://hackerone.com/4f1f16ba-10d3-4d09-9ecc-c721aad90f24/embedded_submissions/new). ## How to Apply You can apply to join our Program [here](https://docs.google.com/forms/d/e/1FAIpQLSf3IuyunFH1Rbz_9Bpt2kGBfwSW5QQ1TBkeAzNZrtCP-hRvNA/viewform). We review applications on a rolling basis. If accepted, you will receive an invite via HackerOne. IIf you do not already have a HackerOne account, please create one before applying to the Program so we can invite you directly on the platform. You must use your @wearehackerone.com email alias to create a [Claude Console account](../04-API-Reference/Other/usage-limits.md). ## Disclosure Guidelines & Confidentiality Obligations All Program participants are required to sign a non-disclosure agreement to protect Program confidentiality as a condition for joining. **You may publicly disclose:** - The existence of Anthropic's Model Safety Bug Bounty Program. - Your participation as a selected participant in the Program. **You may not disclose without express permission:** - Any jailbreaks/vulnerabilities (even resolved ones) outside of the Program without express consent from Anthropic. - The testing question set. - Details about the classifiers and safety mitigations. - Information about the models being tested. - Identity of other participants. - Any other information related to the Program, except as expressly permitted above. ## Anthropic’s Use of Data from the Program Participant agrees that all data submitted to Anthropic, including its products and services, in connection with this Program may be used, stored, shared, and/or published by Anthropic indefinitely in furtherance of its safety research, model development, and related purposes without further obligation to Participant. --- ## Models, usage, and limits in Claude Code | Claude Help Center Source: https://support.claude.com/en/articles/14552983-models-usage-and-limits-in-claude-code Path: 22-Safety-Policy/models-usage-and-limits-in-claude-code.md # Models, usage, and limits in Claude Code This guide explains which model you are using, how usage is metered, and how to keep long sessions within their context and usage limits. ------------------------------------------------------------------------ ## How usage is metered How you signed in determines how usage is metered. Everything else about Claude Code behaves the same way regardless. [TABLE] If you signed in with an Enterprise seat, you generally do not need to think about tokens until you reach a limit. If you are using an API key, the **`/cost`** command shows your running spend for the current session. ------------------------------------------------------------------------ ## Choosing a model Run **`/model`** at any time to see which model you're using, check which models are available to your account, and switch between them. Your default model depends on how you signed in and on your organization's settings. As a rough guide: - **Sonnet** is the right choice for the large majority of coding work. It is fast, capable, and cost-efficient. - **Opus** offers deeper reasoning for harder problems such as large cross-cutting refactors, difficult debugging, or architectural decisions. It uses meaningfully more of your quota, so consider switching to Sonnet for routine work. - **Haiku** is the fastest and cheapest option, well suited to quick lookups, simple edits, or high-volume scripted runs. You can change models mid-session without losing your conversation. A common pattern is to plan with Opus and execute with Sonnet. **Note:** Exact model names, versions, and availability change over time. The `/model` command is always the source of truth for your account. ------------------------------------------------------------------------ ## What actually consumes tokens Every turn sends three things to the model: 1. **The conversation so far** — every previous message in this session. 2. **Project context** — your `CLAUDE.md` and any files Claude has read. 3. **Your new prompt.** Of these, the first item grows the fastest. A long debugging session in which Claude has read twenty files and produced fifteen diffs is carrying all of that on every subsequent message. This is where both cost and context limits originate. ------------------------------------------------------------------------ ## Managing the context window The **context window** is the maximum amount of text the model can consider at once. Claude Code shows a live indicator of how full it is. When it fills up, Claude can no longer see the oldest parts of the conversation clearly and quality drops. Two commands keep it under control: - **`/clear`** wipes the conversation and starts fresh. Your `CLAUDE.md` and project files remain available; only the chat history is removed. Use this whenever you switch tasks, as it is the single most effective lever for both quality and cost. - **`/compact`** summarizes the conversation so far into a short recap, freeing up space while preserving the essential context. Use this when you are mid-task and need to keep going. Claude Code also auto-compacts when you get close to the limit, so you will rarely hit a hard wall. **Rule of thumb:** use `/clear` when starting a new task, and `/compact` when continuing a long one. ------------------------------------------------------------------------ ## Five habits that stretch your usage furthest Almost every "I burned through my limit by lunchtime" report traces back to one of these five. ### 1. Clear between tasks Every previous message is resent on every turn, so a session that has wandered through three unrelated problems pays for all three on each new message. **In practice:** you just finished debugging a login redirect and now want to write a database migration. Run `/clear` first. A simple test: if your next prompt would make perfect sense in a brand-new terminal, clear before sending it. Your `CLAUDE.md` and project files stay put; only the chat history goes. **One warning:** `/clear` cannot be undone. If you might still need something from the history, copy it out first or run `/compact` instead, which preserves a summary rather than wiping everything. ### 2. Match the model to the job Opus costs several times more per turn than Sonnet, and Sonnet more than Haiku. Spending Opus on routine work is the fastest way to drain a daily limit. **Reasonable defaults:** Sonnet for most coding (features, tests, known bugs, refactors); Opus when you're genuinely stuck or the change is wide (hard debugging, cross-cutting refactors, architecture calls); Haiku for quick mechanical work (renames, log lines, regex explanations, boilerplate). ### 3. Point at files instead of pasting them Anything you paste sits in context, in full, for the rest of the session. Referencing a file by path lets Claude read selectively and focus on the part you care about. **In practice:** instead of pasting `auth.ts`, write look at the `validateToken` function in `src/auth.ts` — mentioning the path lets Claude open and read selectively. (Note that the @ prefix injects the entire file plus its `CLAUDE.md` tree into context, so use a bare path when you are trying to *save* tokens.) For logs and stack traces, trim to the relevant 20 or 30 lines before pasting. For anything large (lockfiles, build logs, data dumps), put it on disk and reference the path. ### 4. Keep **CLAUDE.md** lean This file is prepended to *every* turn. Prompt caching means turns after the first are billed at the much cheaper cache-read rate, so the dollar cost is lower than the raw line count suggests, but it still occupies context-window space on every message. **The rule: two strikes, keep it tight.** Only add a note the second time you have to correct Claude on the same thing (first-time issues are usually one-offs). Keep the file under roughly 200 lines; if something new needs to go in and there's no room, something old has to come out. **When to update it:** right after a session where you had to correct Claude twice on the same thing. That's when the fix is fresh and takes a minute to write down. Every few weeks, read the whole file and delete anything that is no longer true or whose purpose you can't remember. Stale notes are worse than missing notes because they actively misdirect Claude. ### 5. Ask for a plan before big changes A plan costs a few hundred tokens. A wrong 400-line diff that you revert and regenerate costs thousands, twice, plus the turns spent explaining what went wrong. **In practice:** for anything touching more than two or three files, switch to Plan Mode or just ask: "Before changing anything, list the files you'll touch and what you'll do in each." Read the list, correct it in plain English ("skip `legacy/`, and don't touch the tests yet"), then let it execute. **Pro tip: plan with Opus, execute with Sonnet.** The highest-value use of Opus is writing the plan itself, where deeper reasoning actually pays off. Once a good plan exists, execution is mostly mechanical and Sonnet handles it at a fraction of the cost. This pattern is built in as `/model opusplan`, which uses Opus while planning and Sonnet for execution. Switching models doesn't clear the conversation, so Sonnet still sees everything Opus produced. ------------------------------------------------------------------------ ## What to do when you reach a limit - **Enterprise seat users:** the message tells you when your window resets. In the meantime you can switch to a lighter model with `/model`, or, if your organization allows it, temporarily fall back to an API key. - **API key users:** there is no usage cap, but check `/cost` and your Console or cloud-provider dashboard if spend is a concern. Unexpectedly high numbers almost always trace back to very long sessions that were never cleared. - **Context window full** (which is different from a usage limit): run `/compact` to keep going, or `/clear` if the older history is no longer needed. ------------------------------------------------------------------------ ## Quick reference [TABLE] --- ## Online Safety Contacts | Claude Help Center Source: https://support.claude.com/en/articles/11174660-online-safety-contacts Path: 22-Safety-Policy/online-safety-contacts.md # Online Safety Contacts March 16, 2026 # **Designated Point of Contact for Authorities** Government authorities can contact Anthropic directly by emailing [\[email protected\]](https://support.claude.com/cdn-cgi/l/email-protection#295b4c4e5c45485d465b044047585c405b404c5a6948475d415b4659404a074a4644). This is reserved for government officials seeking a point of contact and for governmental submissions to remove content.   For other types of inquiries, please use the mechanisms described below.  # **Illegal Content Reporting**  For user requests for content removal, please use the mechanisms described [here](https://support.anthropic.com/en/articles/10684638-blocking-and-removing-content-from-claude).  --- ## Our Approach to User Safety | Claude Help Center Source: https://support.claude.com/en/articles/8106465-our-approach-to-user-safety Path: 22-Safety-Policy/our-approach-to-user-safety.md # Our Approach to User Safety March 16, 2026 User safety is core to Anthropic’s mission of creating reliable, interpretable, and steerable AI systems. As we launch new ways for people to interact with Claude, we also expect to see new types of potential harm materialize, whether through the generation of misinformation, objectionable content, hate speech or other misuses. We are actively investing in and experimenting with additional safety features to supplement our existing model safety efforts and are working to provide helpful tools to a wide audience while also doing our best to mitigate harm. Launching new products in open beta allows us to experiment, iterate and hear your feedback. Here are some of the safety features we’ve introduced: - Detection models that flag potentially harmful content based on our [Usage Policy](https://vault.pactsafe.io/s/9f502c93-cb5c-4571-b205-1e479da61794/legal.html#aup). - Safety filters on prompts, which may block responses from the model when our detection models flag content as harmful. - Enhanced safety filters, which allow us to increase the sensitivity of our detection models. We may temporarily apply enhanced safety filters to users who repeatedly violate our policies, and remove these controls after a period of no or few violations. These features are not failsafe, and we may make mistakes through false positives or false negatives. Your feedback on these measures and how we explain them to users will play a key role in helping us improve these safety systems, and we encourage you to reach out to us at [\[email protected\]](https://support.claude.com/cdn-cgi/l/email-protection#334640564140525556474a73525d475b415c435a501d505c5e) with any feedback you may have. To learn more, [read about our core views on AI safety](https://www.anthropic.com/index/core-views-on-ai-safety). --- ## Public Vulnerability Reporting | Claude Help Center Source: https://support.claude.com/en/articles/11427875-public-vulnerability-reporting Path: 22-Safety-Policy/public-vulnerability-reporting.md # Public Vulnerability Reporting March 16, 2026 ## Help us improve AI safety by reporting universal jailbreaks This [form](https://docs.google.com/forms/d/1bjD-H30kVJAbIHnFXKzFcSjkUNjE-mwRHSF7R2uSjYM/viewform?edit_requested=true) allows you to submit universal jailbreaks for ASL-3 uses of concern (meaning elicit information related to biological threats) that you've identified. Universal jailbreaks are techniques that allow users to consistently bypass safety measures across multiple harmful queries. ## Report a security vulnerability The security of our systems and user data is Anthropic’s top priority. We appreciate the work of security researchers acting in good faith in identifying and reporting potential vulnerabilities. Please review our [Responsible Disclosure Policy](https://www.anthropic.com/responsible-disclosure-policy), which includes a section on *How to Submit a Report*. Thank you very much for helping us to keep Anthropic safe. --- ## red.anthropic.com — Anthropic Cybersecurity Research Source: https://red.anthropic.com/ Path: 22-Safety-Policy/red-home.md # red.anthropic.com — Anthropic Cybersecurity Research red.anthropic.com is Anthropic's dedicated cybersecurity research site, publishing technical analyses of Claude's capabilities in vulnerability discovery, exploitation, and defensive security. ## Articles ### 2026 | Date | Title | Topic | |------|-------|-------| | Apr 8, 2026 | [Claude Mythos Preview](../19-Reference/2026-mythos-preview.md) | New model with step-change cybersecurity capabilities | | Mar 6, 2026 | [Partnering with Mozilla to improve Firefox's security](../19-Reference/2026-firefox.md) | Claude Opus 4.6 discovers 22 Firefox vulnerabilities | | Mar 6, 2026 | [Reverse engineering Claude's CVE-2026-2796 exploit](https://red.anthropic.com/2026/exploit/) | Deep dive into a Firefox JIT miscompilation exploit | | Feb 5, 2026 | [0-Days](https://red.anthropic.com/2026/zero-days/) | Claude Opus 4.6 finding vulnerabilities at scale | | Jan 14, 2026 | [Property-Based Testing with Claude](https://red.anthropic.com/2026/property-based-testing/) | AI agents for property-based testing in Python | | Jan 8, 2026 | [AI for Critical Infrastructure Defense](../19-Reference/2026-critical-infrastructure-defense.md) | PNNL partnership, water treatment plant simulation | | 2026 | [AI Models on Realistic Cyber Ranges](../19-Reference/2026-cyber-toolkits-update.md) | Multistage attacks using only standard open-source tools | ### 2025 | Date | Title | Topic | |------|-------|-------| | Dec 18, 2025 | [Project Vend Phase Two](https://red.anthropic.com/2025/project-vend-2/) | AI managing vending machines and business operations | | Nov 2025 | [AI for Cyber Defenders](https://red.anthropic.com/2025/ai-for-cyber-defenders/) | Improving Claude's vulnerability detection for defense | | 2025 | [Smart Contracts](https://red.anthropic.com/2025/smart-contracts/) | AI agents find $4.6M in blockchain smart contract exploits | --- ## Report, block, and remove content from Claude | Claude Help Center Source: https://support.claude.com/en/articles/7996906-reporting-blocking-and-removing-content-from-claude Path: 22-Safety-Policy/reporting-blocking-and-removing-content-from-claude.md # Report, block, and remove content from Claude Anthropic supports a variety of ways to allow people to control their content and personal information. As a site owner, you can control what shows up in Claude outputs that use web search. As a user or member of the public, you can report problematic content that another user shares publicly or that you receive in a Claude output. For each type of concern, follow the reporting instructions below. Please note, we reserve the right to suspend users who frequently provide manifestly illegal content and suspend the processing of notices for users who frequently submit notices which are manifestly unfounded. We will provide a warning before suspension. ## How to report safety issues We welcome reports concerning safety issues so that we can enhance the safety and harmlessness of our models. We would also like to hear from you if you identify our safety mechanisms causing any user experience issues. Please report such issues to [\[email protected\]](https://support.claude.com/cdn-cgi/l/email-protection#d8adabbdaaabb9bebdaca198b9b6acb0aab7a8b1bbf6bbb7b5) with enough detail for us to replicate the issue. ## How to block or remove content ### Block or remove websites from Claude web search [TABLE] ### Block or remove content from shared Claude content [TABLE] ### Block or remove content from Claude outputs or shared Claude content [TABLE] --- ## Terms of Service Updates | Claude Help Center Source: https://support.claude.com/en/articles/9190861-terms-of-service-updates Path: 22-Safety-Policy/terms-of-service-updates.md # Terms of Service Updates March 16, 2026 At Anthropic, we review our policies and terms to ensure we’re providing the highest level of protection and clarity for our users. This support article covers the changes to our [Consumer Terms of Service](https://url8792.mail.anthropic.com/ls/click?upn=Lkx8Cped8oFc76RI0OmCv1x2RnLlvUgqfB7RzVLsApSvXyt2orRCkRvrp5vRvHrkM02x8yqyYKxTIS8oXAHw9g-3D-3DfJPg_p0ShPCpPTvtmEuEJGvYe3eZztZgqCzhfInQjZFOB8cYRmzkXlX-2F26zBeoLc5XmuQcIC7AByEcAH6aKBGtzcqbozCwRm-2BFPGZ8TunE3aWyP81EjtJMYEdpRjsVGDi8bK9mMPPBDadFxbbkgmw739a6fHxTbnAi8Y4aCFW42Nzyn3HMexOLV6MJQ2RonSn6heCcZqEyvBkh7G4p1ikXL1I6yft9HcHGhdu1-2BG-2FQyYgk9rdJLRDz2gl-2FdqJEOwYFJNAo74gNvaRKihUP3-2FUP-2BImT68RTvLpJZW84cDDNBnEyceCsra2ryL1x8ixmbViPSic-2FDY82VodR-2FVC-2FFE4sPfHzaekeNRxJ1QfWsFVbfdCLAxUejSPkAGef5ImpnY3vViNI8t7n-2FAbj9PolZu13aEYzJL-2F7LQzKU0WLq8J6xqgXE4vY5aJtasTuusml2A6XwFW-2F95oNGiNMk3EQ94rYU3ZzzDdq0TBqHhCV-2F0dcg3hJp2Z8CdIPbRPl7yGN4tOqRT8-2BR3PgxEC4njObPO7Qne-2Bv0dTtvznflhiMHNxWgYqJ5hNB-2B7T03wQo4RQDlV9ct1yYtoLXpXIdjbCIcN2knP2ekj-2FK63d58EDAOWn313Morx49RRMPpfuOqzFopOJ85GYnwYNfQeiSqTNH4Trw1bM7sgjHSrBFOz8WXL4xvxYZZagHoT2vejvIOh3WeyNBx7l05SzFFTM-2F1sKyVjecSmLTyvuc8hFD3YE8IiIAIpeVVdIMjEBtQYynO0Zn96llK6apib8fLvf2zHKIw9-2BOoAxTBKDnYOb4aalzMKjayA41b7ailwCpHlXSAQYlXuvZyGfyXULmF2hL3lkzKyTVOUafBDqUDUHjfg3vbRljY4ydRU9OU-2FI3pI58FjsOoj-2FcGm8uHJ0nRiTYzFbacJXiyZvA3BiRQihR8D2m563hLFZaTPWvgXyOaWo6p3ta9sqEI-2BeRT3c4V8RCDMqVyx27-2BsnWyFKD8hy6hxLpY1RSbOLxLHtZ-2FkvnvQY1wVQWLt5dmEZwR-2FeTVF7t23IA6rbHMeoTg-3D-3D) that take effect **April 15, 2024**. We encourage you to read our updated [Terms of Service](https://anthropic.com/terms) in full, but here is a summary of key changes: - **Enhanced clarity.** With some help from Claude, we reorganized and simplified our Terms of Service to make them easier to understand. - **“Provider” definition.** We updated the definition of “Providers” to include our affiliates, licensors, distributors, and service providers. We also clarified that our Providers are intended third-party beneficiaries of specified disclaimers and limitations of liability. - **Software updates.** We clarified our terms about software updates, including that we may offer automatic updates to our software to ensure our users have access to the latest version. - **Open Source.** We have also clarified that our software may include open source software and describe how open source license terms interact with our Consumer Terms of Service. --- ## Troubleshoot Claude error messages | Claude Help Center Source: https://support.claude.com/en/articles/12466728-troubleshoot-claude-error-messages Path: 22-Safety-Policy/troubleshoot-claude-error-messages.md # Troubleshoot Claude error messages May 18, 2026 This article explains common error messages and warnings you may encounter when using Claude and provides guidance on how to address them. ## Usage limit warnings and errors Usage limit warnings appear when you're approaching your plan’s limit within a five-hour session: *“Approaching 5-hour limit.”* If you hit your plan’s limit after the warning appears, you’ll see a blocking error message letting you know when you can use Claude again: *“5-hour limit reached - resets \[time\].”* Looking for ways to maximize your Claude usage? Refer to **[Usage limit best practices](https://support.claude.com/en/articles/9797557-usage-limit-best-practices)**. ### Usage credits Paid Claude users with usage credits enabled in Usage settings will see a slightly different usage limit error: *"5-hour limit resets \[time\] - continuing with usage credits."* Note that this will only appear for members with access to usage credits. Refer to these articles for more information about this feature depending on your plan: - **[Manage usage credits for paid Claude plans](../17-Billing-Plans/manage-usage-credits-for-paid-claude-plans.md)** - **[Manage usage credits for Team and seat-based Enterprise plans](https://support.claude.com/en/articles/12005970-)** ## Length limit errors You may encounter a length limit error when your message to Claude exceeds the maximum input length allowed: "Your message will exceed the length limit for this chat. Try attaching fewer or smaller files or starting a new conversation." This error indicates that your message is too long and needs to be shortened before sending it to Claude. For users on paid plans with code execution enabled, Claude automatically manages long conversations by summarizing earlier messages when context limits are approached. This means most users will rarely encounter length limit errors during normal use. Your full chat history is preserved so Claude can reference it even after summarization. In rare cases where you still encounter this error (such as when sending a very large first message), you can: - Break your content into smaller chunks and process them separately - Summarize or extract key sections before sending to Claude - Use Claude to first identify the most relevant portions of your content - Start a new conversation ## Login errors If you see a generic error message when attempting to log in to your Claude account (e.g, "There was an error logging you in"), try the following troubleshooting steps: - Ensure you’re not using a VPN when accessing Claude. - Disable any browser extensions that you currently have active. - Clear your browser’s cache and cookies. If you're still seeing an error, check **[our status page](http://status.claude.com)** for active incidents. ## Capacity constraints Capacity issues occur when Claude’s infrastructure experiences high demand system-wide. When capacity is constrained, you may see this message when chatting with Claude: *"Due to unexpected capacity constraints, Claude is unable to respond to your message. Please try again soon."* **Important:** Capacity constraints are not outages. The system is functioning normally but managing high demand across all users. These issues are temporary and typically resolve as demand patterns shift throughout the day. If you encounter this message, try again in a few minutes. Capacity issues will not appear on our status page because they represent normal load management rather than technical problems. ## Service incidents and outages Service incidents are disruptions where Claude is unavailable or significantly degraded for all or most users. These represent actual technical problems with our systems. To check for confirmed incidents, visit status.claude.com, where you'll find real-time updates on scope, impact, and resolution progress for any active incidents. --- ## How do usage and length limits work? | Claude Help Center Source: https://support.claude.com/en/articles/11647753-understanding-usage-and-length-limits Path: 22-Safety-Policy/understanding-usage-and-length-limits.md # How do usage and length limits work? When working with Claude, you may encounter two different types of limits that work in distinct ways: **usage limits** and **length limits**. Understanding the difference between these can help you use Claude more effectively. ## What are usage limits? Usage limits control how much you can interact with Claude over a specific time period. Think of this as your "conversation budget" that determines how many messages you can send to Claude, or how long you can work with Claude Code, before needing to wait for your limit to reset. Your usage is affected by several factors, including the length and complexity of your conversations, the features you use, which Claude model you're chatting with, and the effort level you've selected. Different subscription plans (Pro, Max, Team, etc.) have different usage allowances, with paid plans offering higher limits. Note that your usage of all different Claude product surfaces (claude.ai, Claude Code, Claude Desktop) counts towards the same usage limit. Learn more about **[changing the model, effort, and thinking settings](../15-Claude-AI-Features/how-can-i-change-the-model-version-that-i-m-chatting-with.md)**. ## How can I get unlimited usage? There are a couple of different ways to increase your usage depending on your plan: - If you're using a paid plan, including Pro, Max, Team, or seat-based Enterprise plans, see these articles for details about purchasing usage credits: - **[Manage usage credits for paid Claude plans](../17-Billing-Plans/manage-usage-credits-for-paid-claude-plans.md)** - **[Manage usage credits for Team and seat-based Enterprise plans](https://support.claude.com/en/articles/12005970-)** - If your organization has a usage-based Enterprise plan, your usage is based on consumption. See this article for additional information: **[How am I billed for my Enterprise plan?](../17-Billing-Plans/how-am-i-billed-for-my-enterprise-plan.md)** For strategies to maximize your message allotment, see **[Usage limit best practices](https://support.claude.com/en/articles/9797557-usage-limit-best-practices)**. ## What are length limits? Length limits relate to Claude's context window—the amount of information Claude can work with in a single chat. Think of the context window as Claude's working memory that determines how much content it can process and remember at once. **Note**: The context window size depends on which model you're using. On paid plans, the newest models support up to a 1M token context window, while others support 500K or 200K tokens. A portion of the context window is always reserved for Claude's response, so the longest possible conversation is slightly smaller than the full window. For the current per-model breakdown, refer to **[How large is the context window on paid Claude plans?](../17-Billing-Plans/how-large-is-the-context-window-on-paid-claude-plans.md)** ## Automatic context management For users with code execution enabled, Claude now automatically manages long conversations. When your conversation approaches the context window limit, Claude summarizes earlier messages to continue the conversation seamlessly. This means you can have longer, more natural conversations with fewer interruptions. Your full chat history is preserved so Claude can reference it even after summarization. You may occasionally see that Claude is "organizing its thoughts" during long conversations—this indicates automatic context management is working. Longer conversations that trigger automatic context management consume more of your usage limit. Try starting a new conversation if you're approaching your usage limit in a longer chat. **Note:** **[Code execution must be enabled](../15-Claude-AI-Features/create-and-edit-files-with-claude.md#h_1c99382190)** for automatic context management. Rare edge cases (such as very large first messages) may still encounter context limits. ## How can I increase the size of Claude’s context window? While you can't increase the fixed context window size for your plan, you can use these strategies to maximize available context space and optimize both your context window and usage limits: - **Utilize projects effectively:** Projects use retrieval-augmented generation (RAG), which allows Claude to work with larger amounts of information more efficiently by only loading relevant content into the context window. - **Shorten project instructions:** Keep your project instructions concise and focused on essential information. Claude performs best when you use project instructions for general context around your project, key guidelines, and Claude's role. Reserve task-specific instructions for the chat itself. - **Remove unused project files:** Regularly clean up files you're no longer actively using in your projects. - **Toggle extended thinking off:** Turn off this feature when you don't need Claude's enhanced reasoning for a particular task. - **Lower the effort level:** Choose a lower effort level for routine tasks that don't need Claude's most thorough responses. Higher effort uses more tokens. - **Turn off tools you don't need:** Turn off apps you've connected when a conversation doesn't need them, and ask Claude not to search the web when you don't need current information. **Note:** Tools and connectors are token-intensive, so managing them helps both maximize your available context window and optimize your usage limits. ## Key differences The main distinction is that usage limits control *how much* you can use Claude across all your conversations, while length limits control *how long* any single conversation can become. Usage limits are about quantity over time, while length limits are about the depth and complexity of individual conversations. If you hit your usage limit, you'll need to wait for it to reset, upgrade your plan, or purchase usage credits. If you hit a length limit, you can start a new conversation or use **[features like projects](https://support.claude.com/en/articles/9517075-what-are-projects)** to work with larger amounts of information more efficiently. --- ## Updates to our Acceptable Use Policy (now “Usage Policy”), Consumer Terms of Service, and Privacy Policy | Claude Help Center Source: https://support.claude.com/en/articles/9301722-updates-to-our-acceptable-use-policy-now-usage-policy-consumer-terms-of-service-and-privacy-policy Path: 22-Safety-Policy/updates-to-our-acceptable-use-policy-now-usage-policy-consumer-terms-of-service-and.md # Updates to our Acceptable Use Policy (now “Usage Policy”), Consumer Terms of Service, and Privacy Policy March 16, 2026 At Anthropic, we periodically review our policies and terms to ensure we’re providing the highest level of protection and clarity for our users. As our products evolve, we also want to keep you informed about our latest updates: - Claude is now available as an iOS app via the [Apple App Store](https://apps.apple.com/app/claude/id6473753684) so you can access Claude from anywhere, any time. - For businesses looking to increase productivity, our new [Team plan](../15-Claude-AI-Features/product-overview.md) offers increased usage for members and better tools for managing users and billing. - And Claude.ai is now available to users in the EU. This support article covers some recent changes to our Anthropic’s **[Acceptable Use Policy (now “Usage Policy”)](https://www.anthropic.com/legal/aup)**, **[Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms)**, and **[Privacy Policy](https://www.anthropic.com/legal/privacy)**. We encourage you to read the updated documents on our website, but here is a summary of key changes: Usage Policy - **Policy refinements:** We’ve refined and restructured our policy to give more details about the individuals and organizations covered by our policies. - **More specific risk levels:** We’ve broken out some specific “high-risk use cases” that have additional requirements due to posing an elevated risk of harm. - **Disclosure requirements:** We added new disclosure requirements so that organizations who use our tools also help their own users understand they are interacting with an AI system. Consumer Terms of Service - **Enhanced clarity:** With some help from Claude, we simplified some terms to make them easier to understand. For example, Claude helped us simplify the provision that describes what happens if you create a Claude.ai account with an email domain that belongs to your employer or another organization. - **Update for UK consumers.** For individuals based in the United Kingdom, our UK Consumer Terms of Service now state that the agreement is between the user and our Irish subsidiary, Anthropic Ireland, Limited, rather than Anthropic, PBC. Privacy Policy - **Data controller:** We’ve updated our **[Privacy Policy](https://www.anthropic.com/legal/privacy)** to reflect that the data controller for our users in the European Economic Area (EEA), UK, and Switzerland is Anthropic Ireland, Limited. - **Data retention:** We’ve changed our [default data retention period](../13-Enterprise-Admin/how-long-do-you-store-personal-data.md) to 30 days. You can review our full **[Usage Policy](https://www.anthropic.com/legal/aup)**, **[Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms)**, and **[Privacy Policy](https://www.anthropic.com/legal/privacy)** on our website. If you have any questions, please contact us [here](https://support.anthropic.com). Thanks for using Claude! We appreciate you taking the time to stay informed on these updates as we work to responsibly deploy our products more broadly. --- ## Use analytics chat to ask Claude about usage | Claude Help Center Source: https://support.claude.com/en/articles/14729354-use-analytics-chat-to-ask-claude-about-usage Path: 22-Safety-Policy/use-analytics-chat-to-ask-claude-about-usage.md # Use analytics chat to ask Claude about usage July 1, 2026 Analytics chat lets you ask Claude questions about your organization’s usage in plain language. Instead of clicking through dashboard tabs or exporting data, type a question. Claude runs the right query against your organization’s data and responds with a chart and a short summary of what it found. Analytics chat is available on the Enterprise plan. Access requires the same permissions as the rest of the analytics dashboard. ## Access analytics chat If you can already see the **All activity** view under Analytics, you have access to analytics chat. 1. Sign in to your Claude account. 2. In the left sidebar, select “Analytics.” 3. Click the “Analytics Chat” tab. ------------------------------------------------------------------------ ## How it works Type a question, or select one of the suggested prompts below the input box. Claude matches your question to the closest supported query, runs it against your organization’s pre-aggregated usage data, and returns: - A chart, table, or stat card rendered directly in the conversation, which you can expand, drill into, and export. - A brief written summary calling out the key trend or numbers. You can follow up in the same conversation. Claude keeps context, so you can refine a result ("what about just last week?"), drill in ("break that down by product"), or pivot to a related metric without starting over. ------------------------------------------------------------------------ ## What you can ask Analytics chat answers questions across these areas. ### Active users and adoption - "Show me daily, weekly, and monthly active users" - "How did our key metrics change week over week?" - "Is our stickiness going up or down?" ### Spend - "Show me daily spend for the last 30 days" - "Break down spend by model" - "Compare spend on Claude vs Claude Code" - "What's our cost per active user?" - "What will we spend this month at the current rate?" ### Seats and users - "What's our seat utilization rate?" - "Which seats haven't been used in 30 days?" - "Who are our top spenders?" - "Who are our least active users?" - "How many pending invites do we have?" ### Groups and teams - "Which teams doubled their Claude usage this month?" - "Where are we getting the most value per seat?" - "Show me spend by group" ### Claude Code and Claude Cowork - "Show me Claude Code adoption" - "What percentage of our users are using Claude Code?" - "Show me Cowork adoption" - "Which connectors are Cowork users using?" ### Connectors and skills - "Which connectors are being used?" - "Which skills are being used most?" By default, results cover the **last 30 days**, but you can specify a different range in your question. For example: "show me daily spend since January 1." ------------------------------------------------------------------------ ## Review the results ### The chart is the answer It renders inline, and Claude’s summary below it calls out direction and magnitude of change—for example, "spend dropped roughly 40% starting March 12." Claude won’t judge whether a number is good or bad for your organization, but you can ask it to compare against a prior period. ### Data is refreshed daily Analytics chat reads from tables that are typically updated within one to two days. The date shown on each result reflects the most recent data available and isn’t real-time. ### User-level results are capped Queries that list individual users (top spenders, inactive seats, least active users) return up to 20 users at a time. ------------------------------------------------------------------------ ## Export and share results When Claude returns a chart, hover over it and click to download it. You can share the exported file with stakeholders who don't have access to the analytics dashboard. ------------------------------------------------------------------------ ## Limitations - **Analytics questions only.** Analytics chat is scoped to your organization’s usage data. If you ask an unrelated question, Claude will suggest starting a regular conversation instead. Web search, file uploads, and connectors aren't available here. - **Your organization only.** Results are always scoped to the organization you’re signed into. Cross-organization comparisons aren’t available. ------------------------------------------------------------------------ ## Tips - **Start with a suggested prompt.** The chips below the input show common starting points. Selecting one is the fastest way to see what's available, and you can refine from there. - **Ask follow-ups instead of starting over.** After any chart, "now compare that to last month" or "show me just Claude Code" will refine the result in place. - **Be specific about dates.** "Last 30 days" is the default; say "for March" or "year to date" to change the window. ------------------------------------------------------------------------ ## Troubleshooting ### A query times out or shows raw data instead of a chart Queries can take up to two minutes for large organizations. If one repeatedly fails, try a shorter date range, or contact support and include a screenshot of the result. ### Data looks out of date Check the date shown on the result. The underlying data typically lags by one to two days. If it’s more than two days behind, **[contact Support](https://support.claude.com/en/articles/9015913-how-to-get-support)**. ### The Analytics Chat tab is missing Confirm your organization is on the Enterprise plan and that your account has access to the analytics dashboard. If you’re an admin and still don’t see it, contact your Anthropic account team. --- ## Use Claude Security | Claude Help Center Source: https://support.claude.com/en/articles/14661296-use-claude-security Path: 22-Safety-Policy/use-claude-security.md # Use Claude Security August 27, 2026 ## Overview Claude Security is a capability built into Claude that scans codebases for security vulnerabilities and suggests targeted patches for human review. It helps teams find and fix issues that traditional methods often miss. Learn more **[about Claude security](../15-Claude-AI-Features/product-claude-security.md)**. Claude Security is now available in public beta for users on Enterprise plans. Claude Security allows you to: 1. **Scan your code in parallel** — Claude Security understands context, traces data flows across files, and identifies complex, multi-component vulnerability patterns that traditional scanners might not detect. 2. **Validate findings** — Every finding goes through multi-stage verification, with Claude challenging its own results before surfacing them. The result: more real issues reported and fewer false positives. 3. **Review and patch** — Move from a finding into a Claude Code session to review the proposed fix. Resolve vulnerabilities quickly instead of growing a backlog. Learn how to get started and how leading enterprises use the tool here: **[Getting started with Claude Security](https://claude.com/resources/tutorials/getting-started-with-claude-security)**. ------------------------------------------------------------------------ ## Enable Claude Security An organization owner can enable Claude Security by going to **[Organization settings \> Claude Security](https://claude.ai/admin-settings/claude-security)** and switching the **Turn on for your organization** toggle on. ------------------------------------------------------------------------ ## Finding types Finding falls into these example categories below. **Injection (SQL, Command, Code, XSS):** Untrusted input changes query structure or gets executed. E.g., ' OR 1=1--, ; rm -rf /, \ in a comment. **Injection (XXE, ReDoS):** Parsers or regex abused by crafted input. E.g., XML \ reading /etc/passwd. **Path & Network (Path traversal, SSRF, Open redirect):** Input controls file paths, request destinations, or redirects. E.g., ../../etc/passwd, fetching [http://169.254.169.254/](http://169.254.169.254/). **Auth & Access (AuthN bypass, PrivEsc, IDOR/BOLA, CSRF, Race):** Access checks missing, skippable, or racey. E.g., GET /orders/123 returns someone else's order. **Memory Safety (Buffer/integer overflow, UAF, unsafe misuse):** Input writes past bounds, wraps arithmetic, or hits freed memory. Mostly C/C++/Rust unsafe. **Cryptography (Timing leaks, algorithm confusion, weak primitives):** Secret-dependent branches, JWT alg=none, or MD5/SHA-1/DES/ECB in security paths. **Deserialization (Arbitrary type instantiation):** Untrusted bytes drive object construction — pickle, Java readObject, YAML load. Often equals RCE. **Protocol & Encoding (Cache safety, encoding confusion, length-prefix trust):** Layers disagree or trust declared sizes. E.g., cache poisoning via Host header. ------------------------------------------------------------------------ ## Severities Severity is assigned per finding based on exploitability in your codebase, not the category itself—so the same category can land at different severities in different repos. [TABLE] ------------------------------------------------------------------------ ## Finding structure Each finding contains the following fields: - Title — short descriptive name of the finding - Details — description of what the finding is and why it matters - Location — file path and line number, linked to the source - Impact — what could go wrong if this isn’t addressed - Reproduction steps — ordered list of steps to reproduce or observe the issue - Recommended fix — guidance on how to resolve it - Severity — HIGH / MEDIUM / LOW - Status — Open / Dismissed / Resolved - Category — finding type - Repository — repository identifier - Branch — branch name the finding was produced against - Date created — date the finding was created - Shown only if the finding was dismissed: - Dismissal reason - Dismissal note — optional ------------------------------------------------------------------------ ## Troubleshooting ### The security page keeps redirecting to "Install GitHub App" The claude.ai/security page runs a per-user check against your own connected GitHub account, so this can fail for you even though the organization-wide installation is working for others. There are a few potential causes: - **No GitHub account connected in Claude.** Go to [**Customize \> Connectors**](https://claude.ai/customize/connectors) to check this. - **The connected GitHub account isn’t a member of the GitHub organization** where the app is installed. Connect the account that belongs to that organization. - **SSO isn't authorized for that organization.** If your GitHub organization requires SSO, you must authorize the Claude app for it separately. Follow the steps in **[Use the GitHub integration](https://support.claude.com/en/articles/10167454-use-the-github-integration#h_e169a34a57)**. - **Your GitHub organization's IP allow list is blocking the check.** GitHub's "Enable IP allow list configuration for installed GitHub Apps" setting covers traffic from the App itself, such as Code Review, but it doesn't cover this per-user check. To allow it, manually add 160.79.104.0/21 as an organization-level allow list entry. For the full list of ranges, see **[IP addresses](../04-API-Reference/Endpoints/ip-addresses.md)**. ------------------------------------------------------------------------ ## Frequently asked questions - **Product price and cost** — Scans are charged at direct token cost only. There is no additional platform fee for Claude Security. - **Models** — Claude Security runs scans on Claude Mythos 5. Users receive findings without direct model access. Suggested patches open in Claude Code on the Web and can be implemented with whichever models are available in your account. - **Claude Security plugin for Claude Code** — The plugin uses whichever models you have access to in Claude Code. Only the Claude Security product at **[claude.ai/security](https://claude.ai/security)** runs scans on Claude Mythos 5. - **Scan length** — Scan time varies based on the repository and the agent's actions. - **Severity configuration** — as of today, severity is not configurable. - **Non-GitHub repositories** — Repositories hosted on **[GitHub.com](https://github.com)** and GitHub Enterprise Server can be scanned. Other hosting providers are not supported today. - **No Zero Data Retention (No ZDR)** — Anthropic may retain data where required by law or to address Usage Policy violations. - **Scan consistency** — Scans are stochastic by design. Unlike traditional static analyzers, Claude Security uses an agent that adapts its analysis to each run, reasoning over code context rather than applying fixed pattern matches. This enables the depth of analysis needed to catch logic-level vulnerabilities. - **Exporting findings** — You can copy findings, download them as CSV or Markdown, or push them to your own tracking and notification systems via per-project webhooks. See the “getting started” guide. - **Feedback** — Please share your feedback using the in-product feedback icon on the right. - **IP addresses for Github** — Use the following Anthropic guide for IP addresses allowlisting: **[IP addresses](../04-API-Reference/Endpoints/ip-addresses.md)**. If you use GitHub Enterprise Server, your instance must allow inbound traffic from these IP addresses so Claude Security can reach your repositories. **Scope of use:** You will only use Claude Security to scan code that you or your company owns and to which you or your company holds all necessary rights to scan. You will not use Claude Security to scan code owned by or licensed from third parties, including but not limited to open source projects or repositories other than those included in your company's codebase(s). --- ## Use dictation in Claude for M365 - Claude.ai Documentation Source: https://support.claude.com/en/articles/14479591-use-dictation-in-office-agents Path: 22-Safety-Policy/use-dictation-in-office-agents.md ## On this page - [Use dictation](#use-dictation) - [How it works](#how-it-works) - [Why dictation is not available with third-party authentication](#why-dictation-is-not-available-with-third-party-authentication) Features # Use dictation in Claude for M365 Copy pageCopy page Speak your prompts instead of typing them in Claude for Excel, PowerPoint, Word, and Outlook. Copy pageCopy page Dictation lets you speak prompts instead of typing them. Click the microphone icon in the chat input, speak, and see your words appear in the composer in real time. Dictation requires the desktop version of Excel, PowerPoint, Word, or Outlook. It is not available in Office on the web because browser-hosted add-ins cannot access the microphone. On the web, use your operating system’s built-in dictation or your Office application’s dictation feature instead.Dictation is also available only for organizations using direct Claude authentication. It is not supported when Claude for M365 connects through a third-party platform such as Amazon Bedrock, Google Cloud Vertex AI, Azure AI Foundry, or an LLM gateway. See [Use Claude for M365 with third-party platforms](https://support.claude.com/docs/office-agents/third-party-platforms) for platform support details. [​](#use-dictation) Use dictation 1 Start listening Click the microphone icon on the right side of the chat input. The placeholder changes to “Listening…” and the button highlights. 2 Speak your prompt Words appear in the composer as you talk. 3 Stop or send Click the microphone again to stop, or press Enter to stop and send in one step. To select a different microphone, hover over the microphone icon and click the arrow that appears. [​](#how-it-works) How it works When you start dictating, the add-in streams your audio to Anthropic’s transcription service, the same infrastructure that powers dictation in the Claude apps. The transcribed text displays in real time in the composer. Nothing is transcribed on your device. Audio is streamed to Anthropic, which uses a contracted speech-to-text subprocessor to generate the transcript. Audio is not retained after transcription; only the resulting text remains in your composer. [​](#why-dictation-is-not-available-with-third-party-authentication) Why dictation is not available with third-party authentication In third-party environments, Claude for M365 does not send prompts to Anthropic directly. Spoken audio is effectively a prompt, so dictation is not offered there. Use your operating system’s built-in dictation or your Office application’s dictation feature instead. --- ## Using Agents According to Our Usage Policy | Claude Help Center Source: https://support.claude.com/en/articles/12005017-using-agents-according-to-our-usage-policy Path: 22-Safety-Policy/using-agents-according-to-our-usage-policy.md # Using Agents According to Our Usage Policy March 16, 2026 All uses of agents and agentic features must continue to adhere to Anthropic’s Usage Policy. The following are intended to be non-exhaustive illustrations of how our Usage Policy applies to certain agentic uses. As agentic capabilities evolve, we will update this list with additional examples to help users understand what our Usage Policy covers in practice in agentic environments. ## Do Not Use Agents for Surveillance or Unauthorized Data Collection This includes using agents to: - Monitor or track individuals’ online activities, behaviors, or movements without notification or consent - Collect, compile, or analyze personal information to create profiles based on individuals’ protected attributes, sensitive characteristics, or personal circumstances - Use facial recognition or biometric identification software or websites - Conduct mass surveillance across multiple websites or platforms to send communications or engage in any form of targeted actions ## Do Not Use Agents to Generate or Distribute Harmful Content This includes using agents to: - Create websites or domains that mimic legitimate webpages - Generate content that leads to phishing, social engineering, or fraud - Impersonate individuals (private or public) without their consent ## Do Not Use Agents to Engage in Scaled Abuse This includes using agents to: - Spam government services, emergency systems, or crisis helplines - Overwhelm servers with traffic to disrupt services (e.g., DDoS attacks) - Coordinate harassment campaigns across multiple platforms or accounts - Manipulate online polls, voting systems, or traffic metrics - Create or manage multiple accounts to evade detection or circumvent platform safeguards - Engage in click farming or artificial engagement (e.g., through likes or comments) on social media - Automate influence operations or coordinated inauthentic behavior - Bulk report people, users, or content through abuse reporting systems ## Do Not Use Agents for Unauthorized System Access or Manipulation This includes using agents to: - Install malware, backdoors, or monitoring software without authorization - Execute commands that attempt privilege escalation or system exploitation - Perform actions that could compromise critical infrastructure or emergency services - Engage in unauthorized, illegal, or fraudulent financial transactions (such as brokerage or investment advisory activities) or payment processing - Access or modify another person's account using their stored credentials without authorization --- ## Using Databricks for Data Analysis · Claude Academy Source: https://support.claude.com/en/articles/12430928-using-databricks-for-data-analysis Path: 22-Safety-Policy/using-databricks-for-data-analysis.md # Using Databricks for Data Analysis Integrate Claude with Databricks to access organizational data through Unity Catalog using custom functions, vector search, and natural language queries. 15 minClaude.ai [Open Claude](https://claude.ai/new) The Databricks connector provides Claude with access to your organization's internal data through Unity Catalog, enabling analysis of your databases, running custom business logic, and accessing unstructured documents. Databricks provides three separate connectors: one for functions, one for vector search, and one for Genie, each accessing different capabilities within your Databricks workspace. ## Reminder on Databricks Components[](#reminder-on-databricks-components) Before exploring what Claude can do with Databricks, it's important to understand three core components that exist within your Databricks workspace: 1. **Unity Catalog Functions**: Custom Python or SQL functions your organization has created for specific calculations, data transformations, or API integrations. These might include proprietary scoring algorithms, normalized financial calculations, or business-specific data processing logic. 2. **Vector Search**: Semantic search indexes built on your organization's documents and datasets. These allow searching conceptually similar content even when exact keywords don't match. 3. **Genie**: A natural language interface that translates plain English questions into SQL queries against your data. Genie uses metadata about your tables and columns to understand business terminology and generate appropriate queries. ## What This Connector Provides[](#what-this-connector-provides) ### Integration Capabilities[](#integration-capabilities) Through the Databricks integration, Claude can access resources in your workspace: - **Execute Custom Functions**: Claude can run Unity Catalog functions defined by your organization. This includes executing complex business logic, applying calculations, or calling external APIs through functions your team has created. For example, if your organization has built a custom customer health score function, Claude can apply it consistently across analyses. - **Semantic Search**: Using vector search indexes, Claude can find relevant documents and content based on meaning rather than just keywords. This is particularly useful for searching through contracts, research reports, customer feedback, or technical documentation where similar concepts might be expressed in different ways. - **Natural Language Queries**: Through Genie, Claude can translate plain English questions into SQL queries. Instead of writing complex SQL, you can ask questions like "What was our revenue growth last quarter?" and Claude will use Genie to generate and execute the appropriate query. - **Governed Access**: All data access through the connector respects your organization's Unity Catalog permissions and policies. Claude can only access data and execute functions that your user account has permission to use. ### How Claude Uses Databricks Data[](#how-claude-uses-databricks-data) Claude applies Databricks capabilities in several ways to support comprehensive data analysis: - **Multi-Source Analysis**: Claude combines results from database queries, vector searches, and custom functions to provide comprehensive insights. For example, when validating an investment thesis, Claude might query historical financial performance from your portfolio database, search through past due diligence reports for similar sector investments, and apply your proprietary IRR calculation function to model expected returns. - **Iterative Exploration**: Claude can query data, analyze initial results, and refine searches based on findings. This allows for analysis where insights from one query inform the next. - **Custom Logic Application**: By executing Unity Catalog functions, Claude applies your organization's specific rules and calculations. This ensures that proprietary metrics, adjusted calculations, and company-specific logic are applied uniformly across all analyses. - **Contextual Query Building**: When you ask questions in plain English, Claude uses Genie to translate them into appropriate SQL queries. This translation considers your table structures, column names, and relationships to generate accurate queries that match your database structure. - **Pattern Recognition**: Through vector search, Claude can find patterns and similarities across documents and data. This helps in finding related issues, similar transactions, or comparable situations that might not be obvious through traditional keyword searches. ## Setting up the Databricks Connector[](#setting-up-the-databricks-connector) The Databricks integration consists of three separate connectors, each requiring separate setup: 1. **Functions Server:** Accesses Unity Catalog functions for calculations, business logic, and data transformations. 2. **Vector Search Server:** Enables semantic search across indexed documents and datasets. 3. **Genie Server:** Provides natural language to SQL query translation capabilities. Technical details of the Databricks connectors can be found in Databricks's [MCP Server Documentation(opens in new tab)](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp). Authentication with Databrick's connectors is handled via [OAuth(opens in new tab)](https://docs.databricks.com/aws/en/generative-ai/mcp/connect-external-services#connect-claude-connectors-using-oauth) (for [Claude.ai(opens in new tab)](http://claude.ai/) and Claude Desktop) or via a [Databricks Personal Access Token(opens in new tab)](https://docs.databricks.com/aws/en/generative-ai/mcp/connect-external-services#connect-claude-desktop-using-pat) (for Claude Desktop only). ### Adding the Connector as an Organization Owner[](#adding-the-connector-as-an-organization-owner) 1. Navigate to [Admin settings \> Connectors(opens in new tab)](https://claude.ai/admin-settings/connectors). 2. Scroll down and click “Add custom connector" at the bottom of the list. 3. Enter integration URL for [your Databricks workspace(opens in new tab)](https://docs.databricks.com/aws/en/generative-ai/mcp/managed-mcp) 4. Name the integration. Remember that there are three separate Databricks servers, so consider naming each uniquely (e.g., "Databricks UC", "Databricks Genie", "Databricks Search") 5. Click "Add" ### For Individual Users[](#for-individual-users) Learn about [finding and connecting tools(opens in new tab)](../14-Connectors/browse-skills-connectors-and-plugins-in-one-directory.md). ## Common Use Cases[](#common-use-cases) ### Available Resources Example[](#available-resources-example) To illustrate how these capabilities work together, consider a private equity firm with the following Databricks resources configured: ### Tables in this scenario[](#tables-in-this-scenario) 1. **portfolio_companies:** Company details, acquisition information, current valuations, and debt levels 2. **financial_statements:** Period financials including revenue, EBITDA with adjustments, and operational metrics like customer count and churn 3. **market_comparables:** Sector comparable companies with valuation multiples and growth rates 4. **due_diligence_docs:** Repository of due diligence reports, analysis documents, and deal memos ### Unity Catalog Functions in this scenario[](#unity-catalog-functions-in-this-scenario) 1. **calculate_normalized_ebitda():** Applies standard private equity adjustments to reported EBITDA, removing one-time costs and normalizing owner compensation 2. **compute_portfolio_irr():** Calculates internal rate of return and money-on-invested-capital based on cash flows and holding periods 3. **estimate_debt_capacity():** Models maximum leverage capacity with covenant compliance stress testing under various scenarios ### Vector Search Index in this scenario[](#vector-search-index-in-this-scenario) 1. **due_diligence_index:** Semantic search across all due diligence documents, deal memos, and analysis reports ## Portfolio Exit Readiness Analysis[](#portfolio-exit-readiness-analysis) Example input prompt: Which portfolio companies are ready for exit? Show valuation ranges and expected returns based on current market multiples.  Open in Claude For this analysis, Claude might use the different UC Functions and Genie in the following steps: 1. **Genie**: Identify portfolio companies held \>3 years and retrieve their latest financials. 2. **UC Function**: Call `calculate_normalized_ebitda()` for each company to apply PE adjustments. 3. **UC Function**: Execute `compute_portfolio_irr()` to calculate IRR and MOIC for each company. 4. **Genie**: Query market comparables and apply sector multiples to normalized EBITDA for valuation ranges. Claude might then report its results in a summary showing exit-ready companies with IRR, MOIC, and valuation ranges based on current market multiples. ## New Deal Valuation[](#new-deal-valuation) Example input prompt: We're evaluating TechCorp acquisition (SaaS, \$45M revenue, \$12M EBITDA).What's a fair valuation and how much debt can we support? Include previous due diligence records in your analysis.  Open in Claude To complete this request, Claude might follow this workflow: 1. **Genie**: Query market comparables for similar-sized companies in target's sector to establish valuation benchmarks. 2. **UC Function**: Call `estimate_debt_capacity()` with target metrics to model leverage scenarios and stress-test covenant compliance. 3. **Vector Search**: Search due diligence index for relevant value creation playbooks and precedent transactions. 4. **Synthesis**: Combine results to generate valuation range, recommended capital structure, and relevant precedents. Ideally, Claude would then respond with a report on the valuation range and a recommended offer price, while citing sources that lead to its recommendation. ## Covenant Breach Risk Assessment[](#covenant-breach-risk-assessment) Example input prompt: If we see a 15-25% EBITDA decline across the portfolio, which companies risk covenant breaches? What actions should we take?  Open in Claude For this task, Claude might use the following resources: 1. **Genie**: Identify portfolio companies with debt, focusing on those with leverage \>4x. 2. **UC Function**: Call calculate_normalized_ebitda() for each high-leverage company to establish baseline. 3. **UC Function**: Run estimate_debt_capacity() with 15%, 20%, and 25% decline scenarios for each company. 4. **Genie**: Query historical financials to identify companies with deteriorating working capital trends. Claude might then respond with a breach risk analysis, organized by company and scenario. ## Tips for Using Databricks[](#tips-for-using-databricks) - Be specific about what data you are looking for. - Example: Instead of "Analyze customers", try "Show me our top 20 customers by…" - Use "find similar" language for pattern matching - Example: "Find feedback that mentions issues like this complaint." - Remember that all data access permissions follow your Unity Catalog permissions. Claude can only access the data that you can access. - Custom functions provide consistent calculations. Consider adding UC Functions for calculating standardized metrics. - Complex analyses may require multiple steps. Ask for a plan first and review Claude's proposed approach. - [Reminder on Databricks Components](#reminder-on-databricks-components) - [What This Connector Provides](#what-this-connector-provides) - [Setting up the Databricks Connector](#setting-up-the-databricks-connector) - [Common Use Cases](#common-use-cases) - [Portfolio Exit Readiness Analysis](#portfolio-exit-readiness-analysis) - [New Deal Valuation](#new-deal-valuation) - [Covenant Breach Risk Assessment](#covenant-breach-risk-assessment) - [Tips for Using Databricks](#tips-for-using-databricks) --- ## Using Egnyte for data room management with Claude · Claude Academy Source: https://support.claude.com/en/articles/12651659-using-egnyte-for-data-room-management-with-claude Path: 22-Safety-Policy/using-egnyte-for-data-room-management-with-claude.md # Using Egnyte for data room management with Claude Set up and use the Egnyte connector with Claude for secure document management, search, analysis, and AI-powered content retrieval. 15 minClaude.ai [Open Claude](https://claude.ai/new) The Egnyte connector provides Claude with secure access to your organization’s content stored in Egnyte, enabling advanced document search, AI-powered analysis, and intelligent content management. Through the Egnyte Remote MCP Server, Claude can search for files, retrieve document content, ask questions about specific documents, generate summaries, and interact with Egnyte AI capabilities like Copilot and Knowledge Bases. ## What This Connector Provides[](#what-this-connector-provides) ### Integration Capabilities[](#integration-capabilities) Through the Egnyte integration, Claude can access content and leverage AI capabilities in your Egnyte workspace: - **Search and Discovery:** Claude can search for documents and files using both basic and advanced search capabilities. Advanced search includes extensive filtering options such as metadata, date ranges, file types, and similarity search to help locate specific content across your organization’s file repository. - **Document Analysis:** Using Egnyte AI, Claude can ask questions about specific documents, generate AI-powered summaries, and extract key information from files. This allows for quick comprehension of lengthy documents without reading the entire content. - **Intelligent Content Access:** Claude can fetch and summarize the full content of specific documents, making it easy to work with multiple files simultaneously or extract relevant information for analysis. - **Copilot Integration:** Through Egnyte Copilot, Claude can ask questions with optional context from specific files or folders, enabling comprehensive analysis across related documents. - **Knowledge Base Queries:** Claude can query specific Knowledge Bases that your organization has created in Egnyte, providing access to curated information repositories and enabling targeted searches within specialized content collections. - **Governed Access:** All data access through the connector respects your organization’s Egnyte permissions. Claude can only access files and folders that your user account has permission to view, ensuring data security and compliance with organizational policies. ## How Claude Uses Egnyte Content[](#how-claude-uses-egnyte-content) Claude applies Egnyte capabilities in several ways to support comprehensive content management and analysis: - **Multi-Document Research:** Claude combines search results, document content, and AI-powered analysis to provide comprehensive insights. For example, when researching a topic, Claude might search across multiple folders, retrieve relevant documents, and use Egnyte AI to extract key information from each file. - **Contextual Understanding:** By using tools like ask_document and summarize_document, Claude can understand the context and content of files before providing answers or recommendations. This ensures responses are grounded in your organization’s actual documents rather than general knowledge. - **Efficient Information Retrieval:** Claude uses advanced search filters to narrow down results based on metadata, date ranges, file types, and custom fields. This targeted approach helps locate specific information quickly, even in large content repositories. - **Cross-Document Analysis:** Claude can analyze multiple related documents by asking questions across different files, comparing information, and synthesizing insights from various sources within your Egnyte workspace. - **Knowledge Base Utilization:** When your organization has created Knowledge Bases in Egnyte, Claude can query these curated collections for specific information, making it efficient to access specialized or frequently referenced content. ## Setting up the Egnyte Connector[](#setting-up-the-egnyte-connector) Technical details of the Egnyte connector can be found in [Egnyte’s MCP Server Documentation(opens in new tab)](https://developers.egnyte.com/api-docs/remote-mcp-server). Authentication is handled via OAuth 2.0, providing secure access to your Egnyte content. ### Prerequisites[](#prerequisites) Before setting up the Egnyte connector, ensure you have: - An active Egnyte account on Essential, Elite, or Ultimate plans (Gen 4), OR Platform Enterprise or Platform Enterprise Light with the Co-Pilot add-on (Gen 3) - An MCP-compatible AI client ([Claude.ai(opens in new tab)](http://claude.ai/), Claude Desktop, ChatGPT, etc.) - Your Egnyte domain name and credentials for authentication ### Adding the Connector as an Organization Owner[](#adding-the-connector-as-an-organization-owner) 1. Navigate to [Admin settings \> Connectors(opens in new tab)](https://claude.ai/admin-settings/connectors) 2. Click “Add custom connector” 3. Enter the integration URL: [https://mcp-server.egnyte.com/mcp(opens in new tab)](https://mcp-server.egnyte.com/mcp) 4. Name the integration (e.g., “Egnyte”) 5. Click “Add” 6. Click “Connect” and you will be redirected to the authentication page 7. Enter your Egnyte domain and authenticate with your Egnyte credentials 8. Grant the necessary permissions for the integration 9. All Egnyte tools should now appear in Claude ### For Individual Users[](#for-individual-users) Learn about [finding and connecting tools(opens in new tab)](../14-Connectors/browse-skills-connectors-and-plugins-in-one-directory.md). ## Common Use Cases[](#common-use-cases) ### Contract Review and Analysis[](#contract-review-and-analysis) **Use Case:** Legal teams need to review multiple contracts for specific clauses and terms. For this analysis, Claude might use the following workflow: 1. **Advanced Search:** Use the advanced_search tool to locate all contracts in a specific folder, filtering by file type (e.g., PDF) and date range to find relevant documents. 2. **Document Interrogation:** Apply the ask_document tool to query specific clauses or terms within each contract, such as “What are the termination conditions?” or “What is the liability cap?” 3. **Content Summarization:** Generate summaries of key terms using summarize_document to create concise overviews of each contract’s main provisions. 4. **Cross-Document Comparison:** Compare multiple contracts by asking questions across documents to identify common terms, variations in clauses, or outlier provisions. Claude would then provide a comprehensive analysis showing key findings, comparisons across contracts, and any notable clauses requiring attention. ### Due Diligence Research[](#due-diligence-research) **Use Case:** Investment teams need to analyze company documents during due diligence processes. Example input prompt: Search our due diligence folder for documents related to TechCorp’s financials and operations. Summarize the key financial metrics and operational risks.  Open in Claude For this task, Claude might: 1. Search: Use advanced_search with metadata filters to find all TechCorp-related documents in the due diligence folder 2. Content Review: Fetch key documents and use ask_document to extract specific information about financials, revenue, expenses, and operational metrics 3. Risk Analysis: Query documents about operational challenges, market risks, or compliance issues 4. Knowledge Base Query: If available, search relevant Knowledge Bases for industry benchmarks or comparative analysis 5. Synthesis: Compile findings into a structured summary with key metrics, identified risks, and relevant citations Claude would deliver a comprehensive due diligence summary with financial highlights, operational insights, and risk factors drawn directly from the reviewed documents. ### Policy and Compliance Documentation[](#policy-and-compliance-documentation) **Use Case:** HR or compliance teams need to quickly reference organizational policies and ensure compliance. Example input prompt: What is our company’s remote work policy? Are there any recent updates to travel expense guidelines?  Open in Claude For this request, Claude might: 1. Knowledge Base Search: Query the HR Knowledge Base (if configured) for policy documents 2. Document Search: Use search tools to locate policy handbooks and recent policy updates 3. Specific Questions: Apply ask_document to extract relevant policy sections 4. Recent Changes: Filter by date to identify recent policy modifications 5. Copilot Query: Use ask_copilot with context from specific policy folders for comprehensive answers Claude would respond with clear policy information, citing specific documents and highlighting any recent changes to ensure teams have current, accurate guidance. ### Customer Document Repository Search[](#customer-document-repository-search) **Use Case:** Customer success teams need to find specific deliverables, contracts, or correspondence across client folders. Example input prompt: Find all project deliverables for Acme Corp from Q4 2024, and summarize the project outcomes.  Open in Claude For this analysis, Claude might: 1. Targeted Search: Use advanced_search with folder path (Acme Corp), date filters (Q4 2024), and file type filters to locate deliverables 2. Content Retrieval: Fetch identified documents to access full content 3. AI Summarization: Apply summarize_document to each deliverable to extract project outcomes and key results 4. Consolidated Report: Compile summaries into a unified overview of all Q4 2024 deliverables Claude would provide a comprehensive summary of all project deliverables with key outcomes, making it easy for customer success teams to review project history and results. ## Tips for Using Egnyte[](#tips-for-using-egnyte) - Be specific about file locations and criteria when searching. Including folder paths, date ranges, and file types helps Claude locate the exact documents you need. - Example: Instead of “Find the contract”, try “Search for PDF contracts in the Legal/Vendor folder from 2024” - Use natural language when asking questions about documents. The ask_document and Copilot tools understand conversational queries. - Example: “What are the payment terms?” or “Summarize the main risks outlined in this document” - Leverage Knowledge Bases for frequently accessed information. If your organization has created Knowledge Bases, reference them for faster access to curated content. - Example: “Query the HR Knowledge Base for our vacation policy” - Remember that all access respects your Egnyte permissions. Claude can only access files and folders you have permission to view, ensuring security and proper access control. - For complex analyses involving multiple documents, consider providing folder paths or specific file IDs to help Claude locate the right content efficiently. - When working with large document sets, use filters and metadata to narrow results before asking Claude to analyze or summarize content. - [What This Connector Provides](#what-this-connector-provides) - [How Claude Uses Egnyte Content](#how-claude-uses-egnyte-content) - [Setting up the Egnyte Connector](#setting-up-the-egnyte-connector) - [Common Use Cases](#common-use-cases) - [Tips for Using Egnyte](#tips-for-using-egnyte) --- ## Using LSEG for financial market data analysis · Claude Academy Source: https://support.claude.com/en/articles/12662116-using-lseg-for-financial-market-data-analysis Path: 22-Safety-Policy/using-lseg-for-financial-market-data-analysis.md # Using LSEG for financial market data analysis Set up and use LSEG's financial market data integration with Claude for real-time pricing, analytics, and valuation tools across asset classes. 15 minClaude.ai [Open Claude](https://claude.ai/new) The LSEG integration provides Claude with access to LSEG’s comprehensive financial market data ecosystem, spanning across asset classes and domains. This article explains how to set up and use LSEG to retrieve real-time market data, analytics, and perform complex financial calculations. The LSEG integration relies upon Claude’s ability to use remote connectors. ## What This Integration Provides[](#what-this-integration-provides) ### Capabilities[](#capabilities) The LSEG integration enables Claude to access institutional-grade market data, analytics, and valuation tools directly into conversational AI workflows. - **FX Spot Price Calculation:** Get the latest FX spot rates for currency pairs, enabling real-time foreign exchange analysis and multi-currency calculations. - **FX Forward Price Calculation:** Compute tenor FX forward rates for currency pairs and display FX forward points between currency pairs for different tenors, supporting hedging strategies and forward contract analysis. - **Interest Rate Curve Analysis:** Calculate interest rate curves for specific curve references and access comprehensive lists of all interest rate curves maintained by LSEG for yield curve construction and rate projections. - **FX Forward Curve Points:** Calculate FX forward curve points using LSEG-defined forward curves with specific valuation dates, providing detailed term structure analysis for currency derivatives. - **Bond Pricing:** Price bonds using ISIN codes to retrieve current market valuations, yield calculations, and spread measures for fixed income analysis. - **Comprehensive Asset Class Coverage:** Access data and analytics across equities, fixed income, FX, commodities, and other asset classes through LSEG’s extensive database. ## How Claude Uses LSEG Data[](#how-claude-uses-lseg-data) Claude applies LSEG’s market data to support your financial analysis. - Real-Time FX Analysis: Retrieves current spot rates and forward prices for currency pairs to analyze exchange rate movements, calculate cross-rates, and evaluate currency exposures. - Yield Curve Construction: Pulls interest rate curve data to build term structures, calculate forward rates, and analyze the shape of yield curves for interest rate forecasting. - Fixed Income Valuation: Uses bond pricing tools to value securities, compare yields across issuers, and assess credit spreads for portfolio management and trading decisions. - Cross-Asset Analysis: Combines data from multiple asset classes to identify relationships, correlations, and trading opportunities across markets. - Hedging Strategy Development: Leverages forward curve data to structure currency hedges, evaluate hedge effectiveness, and optimize hedging costs. - Market Data Validation: Provides authoritative pricing and reference data to verify quotes, reconcile positions, and ensure data accuracy. ## Setting Up LSEG Integration[](#setting-up-lseg-integration) Technical details of the LSEG Integration can be found in LSEG’s MCP Server Documentation (available soon on LSEG portal). You will need to contact LSEG to get access to the MCP server. ### For Organization Owners[](#for-organization-owners) 1. Navigate to [Admin settings \> Connectors(opens in new tab)](https://claude.ai/admin-settings/connectors). 2. Scroll down and click “Add custom connector” at the bottom of the list. 3. Enter integration URL: [https://api.analytics.lseg.com/lfa/mcp(opens in new tab)](https://api.analytics.lseg.com/lfa/mcp) 4. Name the integration (e.g., “LSEG MCP”) 5. Click “Add” ### For Individual Users[](#for-individual-users) Learn about [finding and connecting tools(opens in new tab)](../14-Connectors/browse-skills-connectors-and-plugins-in-one-directory.md). ## Common Use Cases[](#common-use-cases) ### Currency Exchange Rate Analysis[](#currency-exchange-rate-analysis) Example input prompt: What’s the current USD/EUR spot rate, and what are the 3-month and 6-month forward rates? Calculate the implied forward points for each tenor.  Open in Claude **When to use:** Evaluating currency positions, pricing FX forwards, or analyzing currency basis. **Tip:** Compare spot vs. forward rates to understand market expectations for currency movements. ### Interest Rate Curve Comparison[](#interest-rate-curve-comparison) Example input prompt: Show me the USD SOFR swap curve. Plot the curve and identify any unusual shapes or inflection points.  Open in Claude **When to use:** Assessing interest rate risk, pricing swaps, or understanding monetary policy expectations. **Typical analysis:** Compare curves across different currencies or time periods to identify relative value opportunities. ### Multi-Currency Bond Analysis[](#multi-currency-bond-analysis) Example input prompt: Price the following bonds using their ISIN codes: FR0014012I5 (French government bond) and US91282CNT44 (US Treasury). Compare their yields and calculate the spread.  Open in Claude **When to use:** Portfolio construction, relative value analysis, or credit assessment across sovereign issuers. **Note:** Ensure proper currency conversion when comparing international bonds. ### FX Forward Curve Construction[](#fx-forward-curve-construction) Example input prompt: For AUD/USD, show me the complete forward curve using AONIA and SOFR conventions. Display the forward points and implied forward rates for standard tenors.  Open in Claude **When to use:** Structuring FX derivatives, pricing swaps, or analyzing currency carry strategies. **Works well with:** Custom valuation dates to assess forward pricing at specific points in time. ### Cross-Asset Correlation Analysis[](#cross-asset-correlation-analysis) Example input prompt: Get the USD SOFR curve and EUR ESTR curve, then analyze how they’ve moved relative to each other. Are there any divergences that suggest trading opportunities?  Open in Claude **When to use:** Identifying cross-currency basis trades or understanding global rate relationships. **Key benefit:** LSEG provides consistent data across asset classes for reliable correlation analysis. ### Real-Time Market Data for Trading[](#real-time-market-data-for-trading) Example input prompt: I’m looking at pricing a currency swap. Get me the current EUR/USD spot rate and the EUR ESTR and USD SOFR curves for accurate valuation.  Open in Claude **When to use:** Pre-trade analysis, pricing verification, or mark-to-market calculations. **Why it matters:** Real-time access ensures your analysis reflects current market conditions. ## Tips for Using LSEG[](#tips-for-using-lseg) - Use specific currency pair conventions (USD/EUR, GBP/USD) - Specify tenors clearly for forward rates (3M, 6M, 1Y) - Reference bonds by ISIN codes for accurate pricing - Define valuation dates when working with forward curves - Understand curve conventions (SOFR, ESTR, AONIA) for different currencies - Cross-reference data across tools to validate analysis - [What This Integration Provides](#what-this-integration-provides) - [How Claude Uses LSEG Data](#how-claude-uses-lseg-data) - [Setting Up LSEG Integration](#setting-up-lseg-integration) - [Common Use Cases](#common-use-cases) - [Tips for Using LSEG](#tips-for-using-lseg) --- ## Using S&P global data for financial analysis · Claude Academy Source: https://support.claude.com/en/articles/12220135-using-s-p-global-data-for-financial-analysis Path: 22-Safety-Policy/using-s-p-global-data-for-financial-analysis.md # Using S&P global data for financial analysis Use Claude's Kensho integration to access S&P Global's financial data for comprehensive market and fundamental analysis of public companies. 15 minClaude.ai [Open Claude](https://claude.ai/new) The Kensho LLM-ready API integration provides Claude with access to S&P Global’s financial data, delivering comprehensive market and fundamental data for public companies. This article explains how to set up the Kensho integration and use S&P data for financial analysis, including price history, financial statements, segment data, and business relationships. ## What This Integration Provides[](#what-this-integration-provides) ### Capabilities[](#capabilities) The integration with Kensho’s LLM-ready API enables Claude to access multiple dimensions of S&P Global’s financial and market data: - **Company Identification and Information:** Retrieve company profiles using tickers, ISINs, or CUSIPs, including industry classifications, employee counts, headquarters locations, and operating status. - **Historical Price and Market Data:** Access OHLC prices, volumes, market cap, and enterprise value at daily, weekly, monthly, or yearly frequencies, with adjusted prices for accurate return calculations. - **Financial Statement Access:** Pull complete balance sheets, income statements, and cash flow statements for annual, quarterly, LTM, or YTD periods with customizable date ranges. - **Granular Financial Metrics:** Extract specific line items from 200+ available metrics including revenue, EBITDA, R&D expense, and calculated ratios like debt-to-equity. - **Segment Performance Data:** Access business unit and geographic breakdowns showing how revenue and operating income distribute across divisions (availability varies by company). - **Business Relationship Mapping:** Identify supplier relationships, customer dependencies, and strategic partnerships from SEC filings to assess operational risks. - **Competitor Intelligence:** Retrieve competitor lists from multiple sources including SEC filings, self-identification, and third-party analysis. - **Time Period Management:** Determine latest reporting periods and calculate historical quarters for consistent comparisons across companies with different fiscal years. ### How Claude Uses S&P Global Data[](#how-claude-uses-sp-global-data) Claude applies Kensho's capabilities to support comprehensive financial analysis leveraging S&P Global data: - **Cross-Identifier Lookups:** Automatically handles tickers, ISINs, or CUSIPs, useful for international portfolios or fixed income securities. - **Multi-Period Analysis:** Constructs time series by pulling data across periods, calculating growth rates and identifying trend changes. - **Statement Reconciliation:** Combines data from different statements to calculate derived metrics and verify consistency. - **Peer Group Construction:** Retrieves identical metrics across companies for true apples-to-apples comparisons. - **Relationship Network Analysis:** Maps business ecosystems to reveal concentration risks and strategic positioning not apparent from financials alone. ## Setting Up the Kensho Integration[](#setting-up-the-kensho-integration) Technical details of the Kensho Integration can be found in the [Kensho Integration MCP Server Documentation(opens in new tab)](https://docs.kensho.com/llmreadyapi/mcp). You will need to contact S&P Global to get access to the MCP server. ### For Organization Owners[](#for-organization-owners) 1. Navigate to [Admin settings \> Connectors(opens in new tab)](https://claude.ai/admin-settings/connectors). 2. Scroll down and click “Add custom connector" at the bottom of the list. 3. Enter the Kensho integration URL: [https://kfinance.kensho.com/integrations/mcp(opens in new tab)](https://kfinance.kensho.com/integrations/mcp) 4. Name the integration (e.g., "Kensho S&P") 5. Click "Add" ### For Individual Users[](#for-individual-users) Learn about [finding and connecting tools(opens in new tab)](../14-Connectors/browse-skills-connectors-and-plugins-in-one-directory.md). ## Common Use Cases[](#common-use-cases) ### Comprehensive Company Profile[](#comprehensive-company-profile) Using the Kensho integration, create a complete profile for Microsoft (MSFT) including current market data, latest financial metrics, business segments, and key competitor data from S&P Global. Include market cap, enterprise value, trailing twelve-month revenue and margins, plus geographic revenue breakdown.  Open in Claude This type of comprehensive profile combines multiple data types into a single analytical view. Claude retrieves current market metrics, pulls recent financial performance, and identifies segment breakdowns to show how the business operates across different units and geographies. The competitor identification adds context about the competitive environment. **When to use:** Initial company research or updating investment memos with current information. **Tip:** Request both market data and fundamentals together for a complete overview that includes valuation context alongside operational performance. ### Historical Price Performance Analysis[](#historical-price-performance-analysis) Pull five years of weekly price data for Tesla (TSLA) and calculate the volatility, maximum drawdown, and performance versus the S&P 500. Include adjusted prices to account for any stock splits and show periods of highest volatility.  Open in Claude Historical price analysis using S&P Global data goes beyond simple price charts. Claude can calculate risk metrics like volatility and maximum drawdown while comparing performance to benchmarks. Using adjusted prices ensures that return calculations properly account for corporate actions, providing accurate performance measurement over multi-year periods. **When to use:** Evaluating historical risk-return profiles or backtesting investment strategies. **Note:** Adjusted prices ensure accurate return calculations across corporate actions like splits and special dividends, which is essential for long-term performance analysis. ### Financial Statement Deep Dive[](#financial-statement-deep-dive) Retrieve Apple's last 12 quarters of income statements and calculate the trend in gross margins, operating margins, and R&D as percentage of revenue. Show both the quarterly values and the rolling four-quarter averages to smooth seasonality.  Open in Claude Financial statement analysis through Kensho allows examination of margin trends and cost structure evolution over time. Claude can pull specific line items from S&P Global datasets across multiple quarters, calculate relevant ratios, and apply smoothing techniques to identify underlying trends beyond seasonal fluctuations. This granular approach reveals operational changes that might be obscured in annual reports. **When to use:** Analyzing margin trends, cost structure changes, or earnings quality. **Tip:** LTM calculations help normalize for seasonal businesses, providing clearer trend analysis for companies with significant quarterly variations. ### Competitor Benchmarking[](#competitor-benchmarking) Identify Netflix's competitors from their SEC filings and compare key metrics including subscriber growth, content costs, average revenue per user, and free cash flow margins. Focus on direct streaming competitors they specifically mention as competitive threats.  Open in Claude Competitor analysis combines Kensho's relationship mapping with financial metric comparisons. Claude first identifies competitors from various sources, then retrieves comparable metrics for each company. This approach provides both the competitive landscape view and quantitative performance comparisons, helping assess relative positioning and competitive advantages. **When to use:** Industry analysis or relative valuation work. **Note:** Different source filters provide varying perspectives on competition—SEC filings show who companies view as threats, while third-party sources may identify less obvious competitive dynamics. ### Segment Performance Tracking[](#segment-performance-tracking) Show Amazon's segment breakdown for the last eight quarters, including revenue and operating income by segment. Calculate the growth rates for AWS, North America retail, and International retail, and identify which segments are driving overall margin expansion.  Open in Claude Segment analysis reveals the underlying drivers of consolidated performance. Claude retrieves segment-level financial data to show how different business units contribute to overall results. By tracking segment metrics over time, you can identify which divisions are accelerating or decelerating, understand margin mix shifts, and assess the quality of revenue growth. **When to use:** Understanding business mix changes and identifying growth drivers. **Tip:** Segment data reveals trends not visible in consolidated statements, particularly for conglomerates or companies undergoing business model transitions. ### Supply Chain Analysis[](#supply-chain-analysis) Map NVIDIA's key business relationships including their primary chip manufacturers, major customers, and strategic technology partners. Focus on relationships mentioned in their latest 10-K filing to understand supply chain dependencies and customer concentration risks.  Open in Claude Business relationship mapping through Kensho provides insights into operational dependencies and strategic positioning. Claude identifies suppliers, customers, and partners from regulatory filings in S&P Global datasets, revealing concentration risks and potential vulnerabilities. This network view complements financial analysis by highlighting operational factors that could impact future performance. **When to use:** Assessing operational risks or understanding industry value chains. **Key benefit:** Reveals dependencies not apparent from financial statements alone, such as single-source supplier risks or customer concentration that could impact revenue stability. ## Tips for Using S&P Global Data[](#tips-for-using-sp-global-data) - Use any identifier format (ticker, ISIN, CUSIP) - Claude handles conversion automatically - Request specific date ranges to manage data volume and focus analysis - Combine market data with fundamentals for comprehensive analysis - Check data availability periods using the latest reporting period function - Note that segment data availability varies by company reporting practices - Be specific about which financial statement items you need from the 200+ available metrics - Consider using LTM periods for companies with significant seasonality - Remember that business relationship data comes from disclosed sources and may not capture all partnerships - [What This Integration Provides](#what-this-integration-provides) - [Setting Up the Kensho Integration](#setting-up-the-kensho-integration) - [Common Use Cases](#common-use-cases) - [Tips for Using S&P Global Data](#tips-for-using-sp-global-data) --- ## What are customer-managed encryption keys (CMEK)? | Claude Help Center Source: https://support.claude.com/en/articles/15505325-what-are-customer-managed-encryption-keys-cmek Path: 22-Safety-Policy/what-are-customer-managed-encryption-keys-cmek.md # What are customer-managed encryption keys (CMEK)? June 15, 2026 Customer-managed encryption keys are available to eligible organizations on Enterprise plans and the Claude Platform. A customer-managed encryption key (CMEK) lets your organization provision an encryption key in your own AWS KMS, Google Cloud KMS, or Azure Key Vault and have Anthropic use it to encrypt certain data in Claude, such as your team's chats, projects, and files. You keep full control of the key, and every operation Anthropic performs with your key is recorded in your cloud provider's audit logs. CMEK is optional, and your organization can choose to enable it in place of the default encryption Anthropic provides. For complete details, including what's encrypted, what's disabled or changed, limitations, and setup guides for each cloud provider, see **[Customer-managed encryption keys on Claude API Docs](../04-API-Reference/Other/manage-claude-cmek.md)**. --- ## What is Anthropic’s policy for handling governmental requests for user information? | Claude Help Center Source: https://support.claude.com/en/articles/9519291-what-is-anthropic-s-policy-for-handling-governmental-requests-for-user-information Path: 22-Safety-Policy/what-is-anthropic-s-policy-for-handling-governmental-requests-for-user-information.md # What is Anthropic’s policy for handling governmental requests for user information? March 16, 2026 Trust and transparency are paramount values. Accordingly: 1. Anthropic does not disclose information about customers or end users of our services in response to government requests except in accordance with valid legal process (eg., a validly issued subpoena or warrant). We will make an exception to this policy if we believe there is an emergency that may result in imminent physical harm or death, and providing such information without delay may avert that emergency. 2. We evaluate each request to ensure that it’s legally valid, and we may reject requests that are overly broad or vague. 3. We will also provide users notice if their data is requested, unless we believe we're legally prohibited from doing so, or other rare exceptions apply, including where a child is at risk of harm or in cases of emergency. In particular, if data is sought on an API or enterprise customer, we will generally ask the requester to contact our customer in the first instance. --- ## Where can I learn more about Anthropic's Privacy practices? | Claude Help Center Source: https://support.claude.com/en/articles/10035659-where-can-i-learn-more-about-anthropic-s-privacy-practices Path: 22-Safety-Policy/where-can-i-learn-more-about-anthropic-s-privacy-practices.md # Where can I learn more about Anthropic's Privacy practices? March 16, 2026 Anthropic respects the privacy of everyone that engages with our products! For more information about our privacy practices please visit our [Privacy Center](https://privacy.anthropic.com/). --- ## Why am I receiving an 'Output blocked by content filtering policy' error? | Claude Help Center Source: https://support.claude.com/en/articles/9205721-why-am-i-receiving-an-output-blocked-by-content-filtering-policy-error Path: 22-Safety-Policy/why-am-i-receiving-an-output-blocked-by-content-filtering-policy-error.md # Why am I receiving an 'Output blocked by content filtering policy' error? March 16, 2026 Some Claude users may encounter refusals or errors with the message ‘Output blocked by content filtering policy’. These refusals do not reflect Anthropic’s judgments about the propriety of any content. Instead, they generally arise from Anthropic’s efforts to prevent Claude from being used to replicate or regurgitate pre-existing materials. Anthropic takes these steps because Claude’s purpose is to generate new content and ideas, not to reproduce content that already exists. We also prohibit in our terms and policies use of our services in ways that infringe, misappropriate, or violate intellectual property or other legal rights. We’re mindful that some users may encounter these refusals or errors when they aren’t intending for Claude to replicate or regurgitate anything. We know this can be frustrating, and welcome your feedback and insights as we iterate on our tooling to improve our users’ experiences with our services. Conversely, if you are receiving these messages because you *are* trying to elicit copyrighted content, we may warn you or, in cases of repeat violations, suspend or terminate your account.