Agentdocs MCP

agentdocs-mcp

MCP server for AgentDocs — the collaborative documentation platform where AI agents are first-class citizens.

This package runs the server locally (stdio), for clients that launch one: Claude Code, Claude Desktop, Cursor, Zed and others. It gives them native tools to read, search, create, update, and share AgentDocs pages.

Most apps need no install and no token. Add https://agentdocs.eu/mcp to your AI app

as a custom connector or MCP server, then sign in when your browser opens. AgentDocs

implements OAuth 2.1 with dynamic client registration, so this works in Claude.ai,

Claude Desktop, Claude mobile, ChatGPT, Grok, Grok Bot, Cursor, VS Code, Claude Code,

Codex, Gemini CLI, Zed, opencode and Devin Desktop. The grant covers your documents only

and can be revoked any time at agentdocs.eu → Settings → Connected apps. The hosted

endpoint has 33 tools: the 25 below plus eight for proposed changes, context

collections and page review. Steps for each app are under

Setup.

Listed on the official MCP registry as io.github.hoornet/agentdocs-mcp.

Setup

Hosted: add the URL and sign in

No package to install, nothing to keep updated, and no token to copy. Leave any authentication fields empty, or choose OAuth if the app asks; your browser then opens an AgentDocs consent page where you sign in and approve.

These steps follow each vendor's own documentation as of November 2026, and app menus change often. Claude, Claude Code, ChatGPT, Grok and Grok Bot are tested end to end. More detail: agentdocs.eu/docs/agents.

Hosted, with a token

Use a token where sign-in isn't offered or isn't what you want: apps that only take an API key or header, scripts and CI, or an agent you want to keep inside one space.

https://agentdocs.eu/mcp        (Streamable HTTP)

Authorization: Token

# Claude Code

claude mcp add --transport http agentdocs https://agentdocs.eu/mcp \ --header "Authorization: Token "

Bearer is accepted here as well as Token , because several clients only offer a "Bearer" field. Account tokens and space-scoped tokens both work — a space token confines the session to its own space, exactly as it does over REST.

Local (stdio): this package

The local server always uses an AgentDocs API token:

• Account token — agentdocs.eu → Profile → Regenerate API Token (full access to everything you own), or
• Space token — open a space → Connect an agent. It reaches exactly one space, with the permission you pick: Read only, Read and propose edits, or Read and edit directly. The server detects it and scopes itself to that space, which is the recommended way to sandbox an agent. This package has no proposal tools, so give a propose-only agent the hosted endpoint instead.

Claude Code (local stdio)

claude mcp add agentdocs --env AGENTDOCS_TOKEN=<your-token> -- npx -y agentdocs-mcp

Codex CLI

codex mcp add agentdocs --env AGENTDOCS_TOKEN=<your-token> -- npx -y agentdocs-mcp

or in ~/.codex/config.toml:

[mcp_servers.agentdocs]

command = "npx" args = ["-y", "agentdocs-mcp"] [mcp_servers.agentdocs.env] AGENTDOCS_TOKEN = " "

Claude Desktop / Cursor / Windsurf / Gemini CLI / generic MCP config

In claude_desktop_config.json / .cursor/mcp.json / ~/.codeium/windsurf/mcp_config.json / ~/.gemini/settings.json respectively:

{

"mcpServers": { "agentdocs": { "command": "npx", "args": ["-y", "agentdocs-mcp"], "env": { "AGENTDOCS_TOKEN": " " } } } }

VS Code (Copilot)

Same server block, but .vscode/mcp.json uses a top-level "servers" key:

{

"servers": { "agentdocs": { "command": "npx", "args": ["-y", "agentdocs-mcp"], "env": { "AGENTDOCS_TOKEN": " " } } } }

Zed

In settings.json:

{

"context_servers": { "agentdocs": { "command": "npx", "args": ["-y", "agentdocs-mcp"], "env": { "AGENTDOCS_TOKEN": " " } } } }

Opencode

In opencode.json (project root) or ~/.config/opencode/opencode.json:

{

"$schema": "https://opencode.ai/config.json", "mcp": { "agentdocs": { "type": "local", "command": ["npx", "-y", "agentdocs-mcp"], "environment": { "AGENTDOCS_TOKEN": " " } } } }

pi / oh-my-pi

Base pi ships without MCP support — use the Skill or the plain REST API there. The oh-my-pi (omp) fork does support MCP and inherits servers from configs already on disk (.claude, .cursor, .codex, .vscode, …) — add the standard mcpServers block above to one of those (e.g. .cursor/mcp.json) and restart omp.

Windows

Many MCP clients can't spawn npx directly on Windows (spawn npx ENOENT). Wrap the command in cmd /c:

"command": "cmd",

"args": ["/c", "npx", "-y", "agentdocs-mcp"]

Catalog-based MCP gateways (e.g. the Docker MCP gateway) only run servers

from their curated catalog and can't launch arbitrary npx servers —

agentdocs-mcp isn't listed there yet. Use the hosted endpoint instead:

https://agentdocs.eu/mcp (Streamable HTTP, 33 tools, nothing to install) — see

Hosted, with a token above. Failing that, the

REST API has full parity.

Configuration

Updating

The setup commands above are unpinned (npx -y agentdocs-mcp), so they always resolve the latest published version. To pick up a new release, just restart your MCP client — the client only re-launches the server process on restart. The server prints its version on startup (stderr): agentdocs-mcp vX.Y.Z: connected ….

If npx serves a stale cached copy, force a refresh:

npx -y agentdocs-mcp@latest    # or: npm cache clean --force

Tools

¹ Hidden when running with a space-scoped token.

² path reads a file from the machine this server runs on, so it works on the stdio server only. The hosted agentdocs.eu/mcp endpoint refuses it — there, the "machine" is AgentDocs' production server, and honouring a caller-supplied path would be arbitrary file read. Use source_url or data there.

Pages, spaces, and workspaces are addressable by UUID or human-readable slug path — get_page accepts "my-workspace/my-space/my-page", create_page accepts "my-workspace/my-space", etc. (Slug paths require an account token.)

Notes

• Saves are kept in the page's version history on the server. Read it with list_page_versions and get_page_version, and bring old text back with restore_page_version (or from the AgentDocs UI). A run of saves through one connection within ten minutes is kept as one version.
• The hosted instance may take ~15 s to respond to the first request after being idle (database cold start) — the server absorbs this with a 35 s timeout and one retry.
• Free-tier API limits surface as clear messages with an upgrade link.

Development

npm install

npm run build

End-to-end smoke tests (hit a real AgentDocs instance with YOUR data):

SMOKE_TESTBED_SPACE="workspace-slug/scratch-space-slug" \ SMOKE_KNOWN_PAGE="workspace-slug/space-slug/page-slug" \ node test/smoke.mjs # account token: all tools

AGENTDOCS_TOKEN= node test/smoke-space-token.mjs # space-token mode

The testbed space is written to (pages created and deleted) — use a scratch space.

Security

See SECURITY.md. Report vulnerabilities privately to contact@agentdocs.eu.

License

MIT