Docs

What is DocsMCP?

DocsMCP is a Model Context Protocol (MCP) server designed to provide Large Language Models (LLMs) with access to documentation. It acts as an intermediary, allowing LLMs to query and retrieve information from various documentation sources, including local files and remote URLs.

How to use DocsMCP?

DocsMCP can be configured within development environments like Cursor and VS Code to enable AI agents to automatically access documentation.

Cursor MCP Configuration

To configure DocsMCP in Cursor, create a .cursor/mcp.json file with the following content:

{
  "mcpServers": {
    "docs-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "docsmcp",
        "'--source=Model Context Protocol (MCP)|https://modelcontextprotocol.io/llms-full.txt'"
      ]
    }
  }
}

VS Code MCP Configuration

For VS Code, add a configuration to your .vscode/mcp.json file:

{
  "servers": {
    "documentation-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "docsmcp",
        "--source=Model Context Protocol (MCP)|https://modelcontextprotocol.io/llms-full.txt"
      ]
    }
  }
}

When specifying a source with spaces, ensure the entire string is wrapped in quotes.

Key Features of DocsMCP

• Documentation Access for LLMs: Enables LLMs to retrieve information from specified documentation sources.
• Support for Local and Remote Sources: Can access documentation from local files and remote URLs.
• Model Context Protocol (MCP) Integration: Facilitates communication between LLMs and documentation sources via MCP.
• Available Tools:
  • getDocumentationSources: Lists all configured documentation sources.
  • getDocumentation: Fetches and parses documentation from a given URL or file path.

Use Cases of DocsMCP

• AI-powered Documentation Retrieval: Allows AI agents to quickly find and utilize relevant documentation during development.
• Enhanced LLM Capabilities: Improves the ability of LLMs to answer questions and provide context based on specific documentation.
• Automated Documentation Integration: Seamlessly integrates documentation access into development workflows within Cursor and VS Code.

FAQ about DocsMCP

Q: What is the Model Context Protocol (MCP)? A: The Model Context Protocol (MCP) is a protocol that facilitates communication between LLMs and external data sources, such as documentation.

Q: Can DocsMCP access documentation from private repositories? A: The provided information does not specify support for private repositories. It focuses on general local and remote file access.

Q: Is DocsMCP limited to specific LLMs? A: DocsMCP is designed to work with LLMs that can integrate with the Model Context Protocol. The examples provided are for Cursor AI and VS Code extensions that support MCP.

DocsMCP

A Model Context Protocol (MCP) server that provides documentation access to LLMs.

Overview

DocsMCP enables Large Language Models (LLMs) to access and query documentation from specified sources, whether from local files or remote URLs. It uses the Model Context Protocol (MCP) to facilitate communication between the LLM and documentation sources.

Usage

Cursor MCP Configuration

You can also configure DocsMCP in your Cursor project by creating a .cursor/mcp.json file:

{
  "mcpServers": {
    "docs-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "docsmcp",
        "'--source=Model Context Protocol (MCP)|https://modelcontextprotocol.io/llms-full.txt'"
      ]
    }
  }
}

This configuration allows Cursor AI to use the documentation MCP server automatically when you open your project.

Note:

When specifying a source that contains spaces, ensure to wrap the entire string in quotes. For example: '--source=Model Context Protocol (MCP)|https://modelcontextprotocol.io/llms-full.txt'

VS Code MCP Configuration

You can configure DocsMCP in VS Code by adding a configuration to your .vscode/mcp.json file:

{
  "servers": {
    "documentation-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "docsmcp",
        "--source=Model Context Protocol (MCP)|https://modelcontextprotocol.io/llms-full.txt"
      ]
    }
  }
}

This configuration allows VS Code extensions that support MCP to use the documentation server automatically.

Available Tools

The MCP server provides two main tools:

getDocumentationSources

Lists all available documentation sources that have been configured.

getDocumentation

Fetches and parses documentation from a given URL or local file path.

Parameters:

• url: The URL or file path to fetch the documentation from

License

MIT