cratis-studio-mcp-safety-guidance SKILL.md skillA
cratis-studio-mcp-safety-guidance from cratis/ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cratis/ai/cratis-studio-mcp-safety-guidance@git:20261013.9c1bacbPins git:20261013.9c1bacb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cratis/ai
- Path
.cratis/ai/skills/cratis-studio-mcp-safety-guidance/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261013.9c1bacb, committed Oct 13, 2026
- First version recorded
- Sep 11, 2026
- Size
- 3,798 bytes
- Repository stars
- 4
- License
- MIT
Classify Studio MCP requests and interpret already-redacted output without discovering or invoking operations. Use whenever a user asks an agent to inspect, query, change, navigate, or automate Studio through MCP, or asks whether a Studio MCP operation is safe. No Studio MCP implementation authority is admitted, so every operation remains evidence-blocked.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Studio MCP safety guidance Treat Studio MCP access as access to live product and organization data. This skill classifies intent only. It does not discover, configure, install, or call an MCP server. ## Verified product sources | Source | Purpose | | --- | --- | | Studio public product announcement | Organization-scoped, credential-gated MCP availability, not tool-effect admission | | `Cratis/Studio` | Private repository; implementation evidence is **not admitted** | Studio has an organization-scoped, credential-gated MCP endpoint. Availability and credentials do not establish that an operation is observational. The private repository cannot supply this public skill's required immutable public effect evidence; do not publish its tool names, schemas or implementation details. Treat edits and dynamically delegated work as effectful by default. ## Current authority boundary No Studio MCP implementation source, operation, prompt, resource, schema, or revision is admitted. An empty inventory means **nothing is authorized**; it does not mean the upstream product has no capabilities. Read the classifications before answering: …
Read the whole file at its exact version.
How to install
mdr add cratis/ai/cratis-studio-mcp-safety-guidance@sha256:20d51fce8f97f5cbThe line at the top of this page pins the label git:20261013.9c1bacb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6ciwab5uigcckrnm)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 11, 2026 and Oct 13, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.9c1bacb latest | 2026-10-13 | 9c1bacb | 3,798 B | A | view · diff |
| git:20261012.61560be | 2026-10-12 | 61560be | 3,839 B | A | view · diff |
| git:20261008.9794373 | 2026-10-08 | 9794373 | 3,151 B | A | view · diff |
| git:20260911.75ad9bc | 2026-09-11 | 75ad9bc | 3,124 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3798 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cratis/ai · 4 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6ciwab5uigcckrnm GET https://markdownregistry.com/api/v1/resolve?ref=cratis/ai/cratis-studio-mcp-safety-guidance GET https://markdownregistry.com/api/v1/blob/20d51fce8f97f5cb0592764fed84428979674e05a59e351615f807ce74c8d1e3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.