Skip to main content
Glama
oraichain

RAGFlow MCP

by oraichain

ragflow-mcp

简易 RAGFlow MCP。仅在 RAGFlow 团队发布官方 MCP 服务器之前有效

安装

我们提供两种安装方法。建议使用方法 2(使用 uv),因为它安装速度更快,并且依赖关系管理也更完善。

方法 1:使用 conda

  1. 创建一个新的 conda 环境:

conda create -n ragflow_mcp python=3.12
conda activate ragflow_mcp
  1. 克隆存储库:

git clone https://github.com/oraichain/ragflow-mcp.git
cd ragflow-mcp
  1. 安装依赖项:

pip install -r requirements.txt

方法二:使用 uv(推荐)

  1. 安装 uv(快速 Python 包安装程序和解析器):

curl -LsSf https://astral.sh/uv/install.sh | sh
  1. 克隆存储库:

git clone https://github.com/oraichain/ragflow-mcp.git
cd ragflow-mcp
  1. 创建一个新的虚拟环境并激活它:

uv venv --python 3.12
source .venv/bin/activate  # On Unix/macOS
# Or on Windows:
# .venv\Scripts\activate
  1. 安装依赖项:

uv pip install -r pyproject.toml

运行 MCP Server Inspector 进行调试

  1. 启动 MCP 服务器

  2. 使用以下命令启动检查器:

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

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    A complete MCP server for Retrieval-Augmented Generation with file management and vector memory for agents. Supports multiple document formats (PDF, DOCX, TXT, MD, CSV, JSON) with semantic search using Hugging Face embeddings and ChromaDB for efficient vector storage.
    11
    10 npm
    1
    MIT
  • F
    license
    B
    quality
    C
    maintenance
    A fixed MCP server that interacts with RAGFlow for dataset management and chat operations, handling legacy endpoint errors and providing a fallback to OpenAI-compatible endpoints.
    5
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that indexes documents and serves relevant context to LLMs via Retrieval Augmented Generation (RAG).
    28 npm
    36
    MIT