Skip to main content
Glama
RAGFlow MCP Server

RAGFlow MCP Server

by wang-junjian

RAGFlow MCP Server

RAGFlow API MCP Server,可以查找知识库和聊天。

下载 MCP 开发文档和 RAGFlow API 参考:

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

Components

Tools

  1. list_datasets

    • 列出所有数据集

    • 返回数据集的 ID 和名称

  2. create_chat

    • 创建一个新的聊天助手

    • 输入:

      • name: 聊天助手的名称

      • dataset_id: 数据集的 ID

    • 返回创建的聊天助手的 ID、名称和会话 ID

  3. chat

    • 与聊天助手进行对话

    • 输入:

      • session_id: 聊天助手的会话 ID

      • question: 提问内容

    • 返回聊天助手的回答

Related MCP server: Dify Management MCP

Configuration

[TODO: Add configuration details specific to your implementation]

Quickstart

Install

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

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:

uv sync
  1. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN

  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector \
  uv --directory /Users/junjian/GitHub/wang-junjian/ragflow-mcp-server \
  run ragflow-mcp-server \
  --api-key ragflow-dhMzViYzJlMTM1NjExZjBiNWU5MDI0Mm \
  --base-url http://172.16.33.66:8060

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Available Tools

3 tools
chat聊天C

向聊天助手提问

Inputs: session_id (required), question (required).

create_chat创建聊天B

创建一个新的聊天助手,基于指定的数据集

Inputs: dataset_id (required), name.

list_datasets列出数据集B

列出 RAGFlow 中的所有数据集

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: chat queries an assistant, create_chat creates a new assistant, and list_datasets retrieves available datasets. No overlap in functionality.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (chat, create_chat, list_datasets), making them predictable and easy to understand.

    Tool Count3/5

    With only 3 tools, the server is minimal. While this might suffice for basic interactions, it feels thin for a full RAGFlow integration.

    Completeness2/5

    The tool set covers only basic operations: chatting, creating a chat assistant, and listing datasets. Missing crucial CRUD operations for datasets and assistants, leaving significant gaps for agents.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers