drio
Open app

RagDocs MCP Server

Source

MCP server for RAG-based document search and management

Catalog onlyCatalog onlySTDIO

Overview

RagDocs MCP Server is a Model Context Protocol (MCP) server that provides RAG (Retrieval-Augmented Generation) capabilities for semantic search and management of documentation using a Qdrant vector database and Ollama/OpenAI embeddings.

To use RagDocs, install it via npm, configure the server with your Qdrant instance and embedding provider, and then utilize the available tools to add, search, list, and delete documents.

  • Add documentation with metadata - Perform semantic searches through documents - List and organize documentation - Delete documents - Support for both Ollama (free) and OpenAI (paid) embeddings - Automatic text chunking and embedding generation - Vector storage with Qdrant
  1. Managing large sets of documents with semantic search capabilities.
  2. Enhancing document retrieval processes in research and data management.
  3. Integrating with applications that require advanced document management features.

Add to your AI client

Use these steps to connect RagDocs 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": {
    "ragdocs-heltonteixeira": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ragdocs-heltonteixeira"
      ]
    }
  }
}

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

Claude Code

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

.mcp.json (project root)

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

VS Code (Copilot)

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

.vscode/mcp.json

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

What are the prerequisites for using RagDocs?

You need Node.js 16 or higher and a Qdrant setup (local or cloud).

Can I use RagDocs with OpenAI embeddings?

Yes, RagDocs supports both Ollama and OpenAI embeddings.

Is there a cost associated with using RagDocs?

Ollama is free, while OpenAI requires a paid API key.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":773,"uuid":"2bfe2482-c183-4949-908f-bbe1c10a9fdf","name":"ragdocs","title":"RagDocs MCP Server","description":"MCP server for RAG-based document search and management","avatar_url":"https://avatars.githubusercontent.com/u/6128503?v=4","created_at":"$D2024-12-30T03:30:48.035Z","updated_at":"$D2025-02-23T07:16:03.490Z","status":"created","author_name":"heltonteixeira","author_avatar_url":"https://avatars.githubusercontent.com/u/6128503?v=4","tags":"ragdocs,document-search,management","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/heltonteixeira/ragdocs","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data