ragflow-mcp

ragflow-mcp

4
developer_tools

The RAGFlow MCP is a simple Model Context Protocol (MCP) server meant to be used temporarily until the official server is released. It offers two installation methods with the second method offering faster installation and better dependency management.

ragflow-mcp

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

Installation

We provide two installation methods. Method 2 (using uv) is recommended for faster installation and better dependency management.

Method 1: Using conda

  1. Create a new conda environment:
conda create -n ragflow_mcp python=3.12
conda activate ragflow_mcp
  1. Clone the repository:
git clone https://github.com/oraichain/ragflow-mcp.git
cd ragflow-mcp
  1. Install dependencies:
pip install -r requirements.txt

Method 2: Using uv (Recommended)

  1. Install uv (A fast Python package installer and resolver):
curl -LsSf https://astral.sh/uv/install.sh | sh
  1. Clone the repository:
git clone https://github.com/oraichain/ragflow-mcp.git
cd ragflow-mcp
  1. Create a new virtual environment and activate it:
uv venv --python 3.12
source .venv/bin/activate  # On Unix/macOS
# Or on Windows:
# .venv\Scripts\activate
  1. Install dependencies:
uv pip install -r pyproject.toml

Run MCP Server Inspector for debugging

  1. Start the MCP server

  2. Start the inspector using the following command:

# you can choose a different server
SERVER_PORT=9000 npx @modelcontextprotocol/inspector