Open Docs (Technical Documentation Search) MCP server

The open-docs-mcp MCP Server provides document management functionality through an MCP (Model Context Protocol) implementation. It allows you to crawl, index, and search documentation from various sources, making it accessible to AI assistants like Claude through the MCP protocol.

Installation

Using NPX

The simplest way to run the MCP server is using NPX:

npx -y open-docs-mcp --docsDir ./docs

Installing via Smithery

If you're using Claude Desktop, you can install the Document Management Server automatically via Smithery:

npx -y @smithery/cli install @askme765cs/open-docs-mcp --client claude

Configuration

Claude Desktop Integration

To use the MCP server with Claude Desktop, you need to edit the Claude configuration file:

macOS:

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

Windows:

%APPDATA%/Claude/claude_desktop_config.json

Add the following configuration:

{
  "mcpServers": {
    "open-docs-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "open-docs-mcp",
        "--docsDir",
        "/path/to/docs"
      ]
    }
  }
}

Configuration Options

The configuration supports these options:

• command: The Node.js executable (usually "npx")
• args: Array of arguments to pass to the script
  • --docsDir: Required parameter that specifies your documentation directory path
• disabled: Optional boolean to temporarily disable the server
• alwaysAllow: Optional array of tool names that can be used without confirmation

Features

Document Management Capabilities

• Crawls and indexes documentation from various sources
• Supports multiple document formats (HTML, Markdown, etc.)
• Provides full-text search across indexed documents
• Automatically re-indexes to keep documentation up-to-date

Using the MCP Server

The MCP Server provides several tools that can be invoked through the MCP protocol:

Available Tools

1. enable_doc - Enable crawling for a specific documentation source
2. disable_doc - Disable crawling for a specific documentation source
3. crawl_docs - Start crawling all enabled documentation sources
4. build_index - Build the search index for crawled documentation
5. search_docs - Search across indexed documentation
6. list_enabled_docs - List all currently enabled documentation sources
7. list_all_docs - List all available documentation sources (enabled and disabled)

Typical Usage Flow

1. Use list_all_docs to see what documentation sources are available
2. Enable specific docs with enable_doc
3. Start the crawling process with crawl_docs
4. Build the search index with build_index
5. Search your documentation with search_docs

These tools can be accessed through any MCP-compatible client, including Claude Desktop when properly configured.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.