Agent Docs MCP Server

by konstantinstarovoytov Your server? Claim it

answering

Agent Docs is answering right now. Last checked 6 min ago. It exposes 2 tools. Last commit 15 Oct 2026.

Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.

Uptime history 70 hours of history

70 hours agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

130 ms

Response time

average over 24h

Stars

last commit 15 Oct 2026

Nothing serious here today

Today is the operative word: we check Agent Docs every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-docs --transport http https://agent-docs-mcp.onrender.com/mcp/

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-docs": {
      "url": "https://agent-docs-mcp.onrender.com/mcp/"
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-docs]
url = "https://agent-docs-mcp.onrender.com/mcp/"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-docs": {
      "url": "https://agent-docs-mcp.onrender.com/mcp/"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "agent-docs": {
      "url": "https://agent-docs-mcp.onrender.com/mcp/"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

docs

search_docs

Search 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 hasn't said which one, ask. Returns one passage per page, with the page's one-line description and a relevance score; under ~0.5 means the docs probably don't cover it. One topic per call: split multi-part questions. Need more than the passage? Call read_section(url), or read_section(url, heading) for one of the passage's other_sections.

section

read_section

Read 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 subsections; use it only on long pages to find one specific subsection.

Endpoints

URL	Transport	State	Latency	Checked
https://agent-docs-mcp.onrender.com/mcp/	streamable-http	answering	223 ms	6 min ago

Alternatives to Agent Docs

same job, measured the same way

RTFM

by roomi-fields

The open retrieval layer for AI agents — index code, docs, data. Search via MCP.

2 130 installs/wk local only

Agent MCP Hub

by blackaxgit

One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

65 installs/wk local only

Genable MCP

by musepy

Write to Figma from any MCP client (Claude Code, Cursor). Complements the read-only official MCP.

56 installs/wk local only

SkillGild

by skillgild

Search and run hosted AI agent skills for Claude Code, Codex, Cursor and Gemini CLI.

local only

showagent

by aytzey

Search, resume and convert AI coding sessions (Claude Code, Codex, Gemini, OpenCode, Pi) over MCP.

local only

Aiko

by masa-san-jp

A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code

410 installs/wk local only

Agent Cowork Memory

by rxthlessbeats

Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

169 installs/wk local only

HeyClaude — Claude & AI workflow directory

by jsonbored

Search the HeyClaude directory of Claude Code agents, MCP servers, skills, and tools.

43 installs/wk 28 tools answering

Agent Docs — questions

Answers built from our own checks of this server.

What can Agent Docs do?

It exposes 2 tools, read directly from the server on our last check. Among them: read_section, search_docs. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Docs working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 130 ms. The bar chart above shows every period we have measured.

How do I connect Agent Docs?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Docs need an API key?

No. Agent Docs completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Docs?

It answers our handshake in 130 ms on average, which is faster than 79% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Agent Docs open source?

Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.