MkDocs MCP Example

Provides an MCP server for AI-assisted access to MkDocs documentation with resource serving and code analysis.

python

0

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "robmatesick-mkdocs-mcp-example": {
      "command": "python",
      "args": [
        "-m",
        "mkdocs_mcp.server"
      ]
    }
  }
}

You can run an MCP server that exposes your MkDocs documentation to an AI-assisted client. This server lets you search, navigate, and extract content from your docs, enabling powerful, interactive access for users and developers alike.

How to use

You connect to the MCP server from an MCP client. Once connected, you can list available documentation pages, search within the docs, and request structured information like page outlines or code blocks. The AI assistant uses your documentation as a knowledge source to answer questions, locate sections, and provide context-aware help. Use the client to browse pages, run full-text searches, and fetch specific page fragments or code examples.

How to install

Prerequisites you need before starting are Python installed on your system. You also need a way to run the MCP server locally, such as using the provided Python runtime.

Then start the MCP server using the runtime command shown here.

{
  "type": "stdio",
  "name": "mkdocs_mcp",
  "command": "python",
  "args": ["-m", "mkdocs_mcp.server"]
}

Additional setup notes

A development flow commonly involves running the documentation site alongside the MCP server. You typically start the docs container or server first and then launch the MCP backend so both services are available during development.

Available tools

search_docs

Full-text search across documentation

find_by_title

Find pages by title or heading

list_pages

List all available documentation pages

get_page_outline

Extract page structure and headings

search_code_blocks

Find and filter code examples