Ragflow MCP Server

🚀 RAGFlow Knowledge Base Conversation Server

The RAGFlow API knowledge base conversation server can be used to search the knowledge base and conduct chats.

Download the MCP development documentation and RAGFlow API reference:

wget https://modelcontextprotocol.io/llms-full.txt -O docs/mcp-llms-full.txt
wget https://github.com/infiniflow/ragflow/raw/refs/heads/main/docs/references/python_api_reference.md -O docs/ragflow-python_api_reference.md

🚀 Quick Start

📦 Installation

GitHub Copilot

.vscode/mcp.json

{
    "servers": {
        "ragflow-mcp-server": {
            "command": "uvx",
            "args": [
                "ragflow-mcp-server",
                "--api-key=ragflow-dhMzViYzJlMTM1NjExZjBiNWU5MDI0Mm",
                "--base-url=http://172.16.33.66:8060"
            ]
        }
    }
}

Continue

config.yaml

mcpServers:
  - name: RAGFlow Server
    command: uvx
    args:
      - ragflow-mcp-server
      - --api-key
      - ragflow-dhMzViYzJlMTM1NjExZjBiNWU5MDI0Mm
      - --base-url
      - http://172.16.33.66:8060

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json%

✨ Features

Tools

1. list_datasets

   • List all datasets
   • Return the ID and name of each dataset

2. create_chat

   • Create a new chat assistant
   • Input:
     • name: The name of the chat assistant
     • dataset_id: The ID of the dataset
   • Return the ID, name, and session ID of the created chat assistant

3. chat

   • Have a conversation with the chat assistant
   • Input:
     • session_id: The session ID of the chat assistant
     • question: The content of the question
   • Return the response from the chat assistant

🔧 Technical Details

Build and Release

1. Synchronize dependencies:

uv sync

2. Install dependencies:

uv install

3. Run tests:

uv test

4. Package:

uv package

Debugging

Use the MCP debugging tool for debugging:

npm install -g @mcp/debugger
mcp-debugger

📚 Documentation

• RAGFlow Python API Reference
• Model Context Protocol

Through these steps, you can easily integrate and use the RAGFlow Knowledge Base Conversation Server into your project.