drio
Open app

RAG Documentation MCP Server

Source

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

Catalog onlyCatalog onlySTDIO

Overview

The RAG Documentation MCP Server is an implementation providing tools for efficient retrieval and processing of documentation through vector search, aimed at enhancing AI assistants' responses with contextual documentation.

To use the server, integrate it with your AI system, ensuring the proper configuration of environment variables such as OpenAI API key and Qdrant credentials. Start the server using specified commands in your configuration file.

  • Vector-based documentation search and retrieval - Supports multiple documentation sources - Semantic search capabilities - Automated documentation processing - Real-time context augmentation for LLMs
  1. Enhancing AI chatbots with relevant documentation answers.
  2. Building intelligent documentation-aware virtual assistants.
  3. Implementing semantic search functionality for technical documents.
  4. Augmenting existing knowledge bases with real-time context.

Add to your AI client

Use these steps to connect RAG Documentation MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-ragdocs-hannesrudolph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-ragdocs-hannesrudolph"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-ragdocs-hannesrudolph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-ragdocs-hannesrudolph"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-ragdocs-hannesrudolph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-ragdocs-hannesrudolph"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-ragdocs-hannesrudolph": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-ragdocs-hannesrudolph"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-ragdocs-hannesrudolph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-ragdocs-hannesrudolph"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-ragdocs-hannesrudolph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-ragdocs-hannesrudolph"
      ]
    }
  }
}

FAQ

Can the MCP Server process documentation from any source?

Yes, as long as the sources are publicly accessible and properly indexed.

Is there a limit to the number of documents that can be processed?

While there is no hard limit, practical constraints such as performance and resource availability may apply.

How do I remove a document from the system?

You can remove documents by specifying their URLs in the remove_documentation tool.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":435,"uuid":"b9575762-fa6b-416d-b0f2-0931b7dd37b0","name":"mcp-ragdocs","title":"RAG Documentation MCP Server","description":"An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.","avatar_url":"https://avatars.githubusercontent.com/u/49103247?v=4","created_at":"2024-12-19T02:11:18.754Z","updated_at":"2024-12-19T12:38:50.832Z","status":"created","author_name":"hannesrudolph","author_avatar_url":"https://avatars.githubusercontent.com/u/49103247?v=4","tags":"mcp,rag,vector-database,llm,mcp-servers","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/hannesrudolph/mcp-ragdocs","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"186\",\"license\":\"MIT license\",\"language\":\"\\n \",\"is_official\":false,\"latest_commit_time\":\"2024-12-16 20:48:48\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data