Agent Docs
概览
作者提供的说明(英文原文)
Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i3 项中通过 3 项依据公开信息检查;尚未扫描代码
- 使用情况i非常新★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 搜索与 AI 记忆
- 你需要填写:X-Cohere-Api-Key, Authorization
安装
选择你使用的 AI 应用,然后复制设置。
安装之前
- 基础检查:3 项中通过 3 项
- 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
- 可以做 2 件事(工具) search_docs, read_section
- 需要你自己填写:
X-Cohere-Api-Key,Authorization
标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
- 在云端运行无需安装任何东西,通过互联网连接
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http agent-docs https://agent-docs-mcp.onrender.com/mcp/ --header 'X-Cohere-Api-Key: your-value' --header 'Authorization: Bearer {token}'运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"agent-docs": {
"url": "https://agent-docs-mcp.onrender.com/mcp/",
"headers": {
"X-Cohere-Api-Key": "your-value",
"Authorization": "Bearer {token}"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"agent-docs": {
"type": "http",
"url": "https://agent-docs-mcp.onrender.com/mcp/",
"headers": {
"X-Cohere-Api-Key": "your-value",
"Authorization": "Bearer {token}"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
需要你填写的值
X-Cohere-Api-Key机密 HTTP headerYour own Cohere API key (free trial at dashboard.cohere.com). Provide this or Authorization.Authorization机密 HTTP headerBearer token from the owner. Provide this or X-Cohere-Api-Key.
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它能做什么
工具名称和描述与服务器在 2026年11月8日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
search_docsSearch the official documentation of Claude Code, Cursor, OpenAI Codex and MCP. Use it before answering any question about using, configuring or administering these products. Not for other products or general programming. If the answer could differ between products and the user h
read_sectionRead a page found by search_docs. Without a heading: the page's description and outline (top-level sections with subsection counts). With a heading: that section's full text, including its subsections; continue long sections with next_offset. outline_depth=3 also lists subsection
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 KonstantinStarovoytov 验证,该账户拥有此仓库
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- ✓ 通过
端点有响应
在 137 毫秒内响应(HTTP 200)
- – 不适用
使用 OAuth 登录
无需登录
- ✓ 通过
工具描述中没有隐藏指令
已读取 2 个工具描述,未发现针对 AI 的隐藏指令
与“搜索与 AI 记忆”中的其他服务器比较i
- 星标数多于此分类中其他 5686 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 5686 个服务器的 62% 更新
- 基础检查结果等于或优于此分类中其他 5686 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Agent Docs 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
你需要填写:X-Cohere-Api-Key, Authorization
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于–,最新版本(0.1.1)于24天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
有什么可以替代它?
同一分类中有:Context7, Codebase Memory, Exa
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Exa
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Agent Docs
An MCP server that gives AI agents the current official documentation of Claude Code, Cursor, Codex and MCP.
These tools change faster than a model's training data. Agent Docs keeps about 600 pages of their official docs in a search index, refreshes it every day, and gives your agent two tools: one finds the right passage, the other reads a whole section. The agent answers from the real docs and can link to them.
It runs as a remote MCP server (and over REST). You can try it with a free Cohere key.
[Step through it at your own pace](https://konstantinstarovoytov.github.io/agent-docs/) (arrow keys work), or open the stills:
The 15 steps as still images
Source and how to rebuild: docs/flow/
How it was built and what was measured: ARCHITECTURE.md.
Connect
Add the server to any MCP client (Claude Code, Cursor, OpenWebUI and others):
{
"mcpServers": { "agent-docs": { "url": "https://agent-docs-mcp.onrender.com/mcp/", "headers": { "X-Cohere-Api-Key": " " } } } }
Calling a tool needs one of two headers:
- Your own Cohere key:
X-Cohere-Api-Key:. A free trial key is at dashboard.cohere.com. The key pays for reranking that one request; it is never stored or logged. Limit: 30 requests a minute per IP. - A token from the owner:
Authorization: Bearer. For a guest token, open an issue titled "Guest token request".
The server is on a free plan: after 15 idle minutes, the first request takes about a minute.
| Tool | What it returns |
|---|---|
search_docs(query, limit=8, product=None, response_format="concise") | The best passage from each matching page, ranked, with the page's one-line description and a relevance score. Ask about one topic per call. product: claude-code, cursor, codex, mcp |
read_section(url, heading=None, offset=0, outline_depth=2) | Without a heading: the page's description and outline (outline_depth=3 adds subsections). With a heading: the whole section, up to 8,000 characters per call (next_offset gives the rest) |
Over REST:
curl -X POST https://agent-docs-mcp.onrender.com/ask \
-H "Authorization: Bearer $API_TOKEN" -H 'content-type: application/json' \ -d '{"question": "How do I add an MCP server in Claude Code?"}'
With your own key, replace the Authorization line with -H "X-Cohere-Api-Key: $COHERE_API_KEY".
| Endpoint | Purpose |
|---|---|
GET /health | Liveness, no token |
POST /ask | A written answer with citations |
POST /search | Passages with page descriptions (search_docs) |
POST /pages | Page cards: description and outline |
POST /section | One section of a page (read_section) |
POST /mcp/ | MCP (streamable HTTP) |
GET /docs | Interactive API docs (use Authorize with the token) |
Locally, without a server (stdio, no token):
{ "mcpServers": { "agent-docs": { "command": "uv",
"args": ["run", "--directory", "/path/to/agent-docs", "rag-mcp"] } } }
For MCP directories: connecting and listing the tools need no key (30 requests a minute per IP); only tools/call does. The server keeps no session, so GET /mcp answers 405; send everything with POST. Listed in the official MCP Registry as io.github.KonstantinStarovoytov/agent-docs (server.json).
What it covers
| Product | Source |
|---|---|
| Claude Code (incl. Agent SDK, plugins) | code.claude.com/docs/llms.txt |
| Cursor | cursor.com/llms.txt |
| Codex | developers.openai.com/codex/llms.txt |
| MCP (latest spec, registry, extensions) | modelcontextprotocol.io/llms.txt |
How it works
Your agent calls search_docs, then read_section when a passage is not enough. No language model runs on the server for this: the agent reads the passages and writes the answer itself.
search_docs works in four steps:
- It searches by meaning (embeddings) and by exact words (BM25) at the same time, so both "connect a tool server" and
claude mcp addfind the right page. - It merges the two result lists by rank. Ties are kept in a fixed order, so the same question always gets the same results.
- A reranker (Cohere) reads the top 20 together with the question and scores how well each one matches.
- It keeps the best passage of each page and adds the page's one-line description and the headings of its other matching sections.
read_section reads from a stored copy of the page; no model is called. Searches are traced in Langfuse.
The REST endpoint /ask is for clients that are not agents. It also translates Russian and Polish questions into English, says "the documentation does not cover this" when even the best candidate scores below 0.55, picks 8 chunks (at most 2 from one section), and has gpt-6-luna write an answer that cites them.
Updated every day
[Step through it at your own pace](https://konstantinstarovoytov.github.io/agent-docs/?flow=reindex), or open the stills:
The 12 steps as still images
Every day at 06:00 UTC a GitHub Actions job reads each vendor's list of pages (llms.txt) and updates the index:
- Changed pages are embedded again; unchanged ones are skipped.
- New pages are checked first. A suspicious one waits in a GitHub issue until the owner ticks Index or Decline.
- Pages that disappear from the list are deleted, unless too many disappear at once.
- A short report of what changed in the products goes to reports/docs-changes/.
Measured results
Each change was measured on labelled que
只显示了开头部分;其余内容请在仓库中阅读