MCP.so
Sign In

ragflow-mcp

@oraichain

About ragflow-mcp

Simple RAGFlow MCP. Only useful until the RAGFlow team releases the official MCP server

Basic information

Category

Other

License

Apache-2.0

Runtime

python

Transports

stdio

Publisher

oraichain

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ragflow-mcp": {
      "command": "uv",
      "args": [
        "venv",
        "--python",
        "3.12"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is ragflow-mcp?

A simple MCP server for RAGFlow, intended as a temporary solution until the official RAGFlow MCP server is released.

How to use ragflow-mcp?

Install via conda or uv (recommended), then start the MCP server and optionally run the inspector with SERVER_PORT=9000 npx @modelcontextprotocol/inspector for debugging.

Key features of ragflow-mcp

  • Simple integration with RAGFlow via MCP protocol
  • Two installation methods: conda and uv
  • Support for MCP Server Inspector debugging

Use cases of ragflow-mcp

FAQ from ragflow-mcp

What is the purpose of ragflow-mcp?

It provides a temporary MCP server for RAGFlow until the official RAGFlow team releases their own MCP server.

How do I install ragflow-mcp?

Two methods are available: using conda (create environment, clone repo, install dependencies with pip) or using uv (install uv, clone repo, create virtual environment, install dependencies with uv pip).

How do I debug the server?

Start the MCP server, then run the inspector with SERVER_PORT=9000 npx @modelcontextprotocol/inspector.

What are the runtime requirements?

Python 3.12 is required. No other dependencies are mentioned beyond those in requirements.txt/pyproject.toml.

Comments

More Other MCP servers