Reader MCP Server
Give AI tools read-only MCP access to your publicly published documentation, so readers can search and reference your docs from ChatGPT, Claude, Cursor, and other MCP clients.
Serve your documentation to AI tools
The Reader MCP Server is your own MCP endpoint, served from your documentation domain. It gives MCP-compatible tools read-only access to your publicly published documentation so they can search, retrieve, and reference your content without any ability to change it.
This is the server your readers connect to: customers, support teams, solution engineers, and internal users, along with the AI tools they work in. If you are looking for the server your documentation team connects to in order to write docs, see the Authoring MCP Server.
The Reader MCP Server was previously called the Docs MCP Server. Only the name changed. Your endpoint, its behavior, and any existing client configurations continue to work unchanged.
The Reader MCP Server is read-only. It does not create, update, delete, or reorganize content, and it does not expose branch management, deployments, or dashboard actions. For those workflows, use the Authoring MCP Server.
Find your endpoint
The Reader MCP Server becomes available as soon as you publish your documentation. There is nothing to provision or enable.
You can find your endpoint in the dashboard under MCP Servers in the sidebar. It follows the same shape as your documentation URL:
https://docs.yourdomain.com/_mcphttps://yourdomain.com/docs/_mcp
Understand what it can access
The Reader MCP Server serves your publicly available published documentation. It sits in front of your published site, not your authoring environment, and it exposes only content that is open to anyone.
Private, password-protected, internal, and partial documentation is not served through the Reader MCP Server today. If your documentation is gated, that content is not available to connected clients.
Authenticated access is on the immediate roadmap as the Reader MCP Server with authentication. It will let a client authenticate with an API key or OAuth to retrieve gated content, together with granular access control that scopes a connected client to specific products, versions, languages, groups, or pages. See the roadmap for status.
Because the server is read-only, it works well when you want grounded answers from trusted documentation while keeping editing controls entirely separate.
The Reader MCP Server is not connected to Documentation.AI workspace roles. The Viewer role on the Authoring MCP Server is unrelated: that role governs your team's access to the project, while the Reader MCP Server serves only what your site publishes publicly.
Configure your MCP client
Add your endpoint to any MCP-compatible client. Replace docs.yourdomain.com with your own documentation domain.
{
"mcpServers": {
"my-docs": {
"command": "npx",
"args": [
"mcp-remote",
"https://docs.yourdomain.com/_mcp",
"--timeout",
"120000"
]
}
}
}
claude mcp add my-docs \
--transport http \
--url https://docs.yourdomain.com/_mcp
{
"mcpServers": {
"my-docs": {
"command": "npx",
"args": [
"mcp-remote",
"https://docs.yourdomain.com/_mcp",
"--timeout",
"120000"
]
}
}
}
For Claude Desktop, add the configuration to claude_desktop_config.json. For Cursor, add it to your mcp.json. For Claude Code, run the command from your terminal, or add the same JSON to a .mcp.json file in your project root.
You can copy your endpoint straight from a documentation page using the Copy MCP server URL page action. See Page Actions.
Available tools
The Reader MCP Server exposes your published documentation through a retrieval tool, searchDocumentation. Connected clients use it to find the most relevant pages, headings, API reference sections, and snippets in your docs.
Your MCP client discovers the tool and its parameters automatically when it connects, so you do not need to configure anything beyond the endpoint itself.
Best-fit use cases
Choose the Reader MCP Server when the goal is documentation retrieval, not documentation management.
- Customer-facing documentation: Let customers connect AI tools to your published docs for product questions, onboarding, and API lookup.
- Support and success workflows: Help your team answer from the same published docs your customers use.
- AI assistants and copilots: Add a retrieval layer over your docs so responses stay tied to current published content.