mcp SKILL.md skillA

mcp from wangqiqi/cursor-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wangqiqi/cursor-ai/mcp@git:20261026.8d01e18

Pins git:20261026.8d01e18 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wangqiqi/cursor-ai
Path
.cursor/harness/core/skills/mcp/SKILL.md
Versions recorded
1
Latest version
git:20261026.8d01e18, committed Oct 26, 2026
Size
4,215 bytes
Repository stars
4
License
none declared

MCP 服务器设计与实现要点:工具边界、命名、分页、错误、传输选型; 建服四阶段流程。参考 reference/ 精简指南。.

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

# mcp

设计与实现 **Model Context Protocol** 服务器时用本 skill。密钥与鉴权清单仍走 **security**。

## 设计要点

- **一工具一职责**;schema 写清参数、默认值与错误
- **命名可发现**:一致前缀 + 动词(如 `github_list_repos`);避免缩写堆砌
- **API 覆盖 vs workflow**:默认优先完整 API 面,便于 Agent 组合;高频多步可另加 workflow 工具
- **上下文**:描述简洁;大结果集须 **分页/过滤**(limit/cursor);返回聚焦字段
- **可行动错误**:指出缺参、合法取值、下一步,勿只抛裸异常字符串
- **只读默认安全**;写/删须明确确认边界
- **无密钥进 repo**;env 或 Cursor MCP 配置注入;日志不泄露 token/PII

## 建服四阶段

### 1 · 调研与规划

1. 读目标服务 API(鉴权、分页、幂等、限流)
2. 列出工具清单:读优先,写操作单独标风险
3. 选型:本地 → **stdio**;远程/可扩展 → **Streamable HTTP**(或项目既有传输)
4. 语言:TS(官方 SDK + Zod)或 Python(FastMCP)— 跟团队栈

详阅:`reference/best-practices.md`

### 2 · 实现

- 参数用 schema 校验(Zod / Pydantic)
- 工具描述写「何时用 / 勿用于」
- 分页参数默认保守(如 limit≤50)
- 外部 HTTP:timeout · 有限重试 · 不吞错误体
- **Tool annotations**(SDK 支持时标注,助 Agent 选型):
  - `readOnlyHint` — 只读查询
  - `destructiveHint` — 删改/不可逆
  - `idempotentHint` — 重复调用安全
  - `openWorldHint` — 开放域/外部实体
- 现代 TS SDK:尽量定义 `outputSchema` / `structuredContent`,便于客户端解析

精简模式见:`reference/typescript-patterns.md` · `reference/python-patterns.md`  
(完整 SDK 以官方文档为准,勿在母版内嵌整份 upstream README。)

吸收自 anthropics/skills/mcp-builder。

### 3 · 审查与测试

- [ ] 无重复巨型「万能」工具
- [ ] 错误信息可行动
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ifsdxpykfu4wke55/21e61e2cd7f95b01e4c7bb7cc64e8fcf6bbed63f7c68caa02a31a8a3a2584fd7.json

Then /plugin install mcp@markdownregistry-ifsdxpykfu4wke55 in Claude Code. It installs git:20261026.8d01e18, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add wangqiqi/cursor-ai/mcp@sha256:21e61e2cd7f95b01

The line at the top of this page pins the label git:20261026.8d01e18, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ifsdxpykfu4wke55.svg)](https://markdownregistry.com/a/art_ifsdxpykfu4wke55)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in wangqiqi/cursor-ai/mcp since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of mcp from somewhere else? Ask it: where did my mcp come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Oct 26, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261026.8d01e18 latest2026-10-26 8d01e18 4,215 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4215 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

GitHub

wangqiqi/cursor-ai · 4 stars · license none declared · pushed 2026-11-17 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_ifsdxpykfu4wke55
GET https://markdownregistry.com/api/v1/resolve?ref=wangqiqi/cursor-ai/mcp
GET https://markdownregistry.com/api/v1/blob/21e61e2cd7f95b01e4c7bb7cc64e8fcf6bbed63f7c68caa02a31a8a3a2584fd7

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.

More from wangqiqi/cursor-ai

learn SKILL.md skill
wangqiqi/cursor-ai · .cursor-plugin/skills/learn/SKILL.md · 学习项目(/learn):CHANGELOG/git/archive→.growing/learn/。不写 .cursor。
git:20261026.a78b4df · audit A · 4 stars
master SKILL.md skill
wangqiqi/cursor-ai · .cursor-plugin/skills/master/SKILL.md · 总入口(/master)— 迷路时 AskQuestion 路由 plan/run/learn 等
git:20261014.d6d51ac · audit A · 4 stars
plan SKILL.md skill
wangqiqi/cursor-ai · .cursor-plugin/skills/plan/SKILL.md · 规划(/plan):需求→先总后分→Sprint→plan.md→/run。说「规划」「拆任务」时用。禁止写业务代码。≠ IDE Plan 模式。
git:20261026.91ca199 · audit A · 4 stars
run SKILL.md skill
wangqiqi/cursor-ai · .cursor-plugin/skills/run/SKILL.md · 执行(/run):gate-check→ACTIVE→验收→审计→CHANGELOG→README→plan→必 commit;任务/Sprint 收尾自动提交。
git:20261026.c0b4a22 · audit A · 4 stars
scaffold SKILL.md skill
wangqiqi/cursor-ai · .cursor-plugin/skills/scaffold/SKILL.md · 脚手架(/scaffold):空项目创建栈模板,已有项目审计与建议。说「初始化」「创建项目」「脚手架」时用。须用户确认后再创建。
git:20261026.a78b4df · audit A · 4 stars
AGENTS.md@.cursor AGENTS.md file
wangqiqi/cursor-ai · .cursor/AGENTS.md
git:20261026.a78b4df · audit B · 4 stars
AGENTS.md@.cursor/harness/core AGENTS.md file
wangqiqi/cursor-ai · .cursor/harness/core/AGENTS.md
git:20261116.6085164 · audit A · 4 stars
api SKILL.md skill
wangqiqi/cursor-ai · .cursor/harness/core/skills/api/SKILL.md · REST/OpenAPI 设计审查。
git:20261116.6085164 · audit A · 4 stars
code-stats-viz SKILL.md skill
wangqiqi/cursor-ai · .cursor/harness/core/skills/code-stats-viz/SKILL.md · 代码统计可视化(关键词):Git 行数/语言分布/提交日历 → HTML 仪表板。说「代码统计」「代码量」时用。
git:20261117.72adeab · audit A · 4 stars
debug SKILL.md skill
wangqiqi/cursor-ai · .cursor/harness/core/skills/debug/SKILL.md · 系统调试循环(无 slash · skill-only)— 复现→假设→隔离→验证→记录;禁止无复现盲改。说「修 bug」「测挂了」「不知道为啥挂」时用。
git:20261026.8d01e18 · audit A · 4 stars
delivery SKILL.md skill
wangqiqi/cursor-ai · .cursor/harness/core/skills/delivery/SKILL.md · 交付验收(/delivery):视觉 · i18n · 文档 · API · 组件 · 可维护 · 生产就绪。Sprint 收尾或 /release 前走查。
git:20261026.8d01e18 · audit B · 4 stars
disk SKILL.md skill
wangqiqi/cursor-ai · .cursor/harness/core/skills/disk/SKILL.md · 磁盘快照(关键词 · 跨平台):采集 HOME 与可配置路径占用 → .growing/disk-snapshots/,并与上次对比。
git:20261026.8d01e18 · audit A · 4 stars

Every file in wangqiqi/cursor-ai

Other files named mcp

mcp SKILL.md skill
alsk1992/cloddsbot · src/skills/bundled/mcp/SKILL.md · Model Context Protocol server management and tool integration
git:20260130.78e49cb · audit A · 3,119 stars
mcp SKILL.md skill
sidiora-labs/codify · plugins/mcp/skills/mcp/SKILL.md · Connect ChatGPT, Claude or another MCP client to this Hyperfide, and list or disconnect the apps that have access.
git:20261031.fc5ea53 · audit B · 638 stars
mcp SKILL.md skill
sidiora-labs/hyperfide · plugins/mcp/skills/mcp/SKILL.md · Connect ChatGPT, Claude or another MCP client to this Hyperfide, and list or disconnect the apps that have access.
git:20261031.fc5ea53 · audit B · 637 stars
mcp SKILL.md skill
nitinjain999/platform-skills · plugins/platform-skills/skills/mcp/SKILL.md · MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol…
git:20261018.90b97a9 · audit B · 72 stars
mcp SKILL.md skill
nitinjain999/platform-skills · skills/mcp/SKILL.md · MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol…
git:20261011.e8166a5 · audit B · 72 stars
mcp SKILL.md skill
thesampadilla/montaj · skills/mcp/SKILL.md · MCP server mode for montaj — load when running as an MCP client (e.g. Claude Desktop)
git:20260930.5b34692 · audit A · 29 stars
mcp SKILL.md skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/mcp/SKILL.md · Configure and manage MCP providers for Agent Toolkit — setup, list, doctor, and per-tool
v1.0 · audit A · 20 stars
mcp SKILL.md skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.opencode/skills/mcp/SKILL.md · Configure and manage MCP providers for Agent Toolkit — setup, list, doctor, and per-tool
v1.0 · audit A · 20 stars

Browse by kind, by grade A, or by owner.