mcpField
R
Ragflow Retrieval Mcp Server

Ragflow Retrieval Mcp Server

Local
github.com/datahwcMemory & Knowledge0Updated 69w ago
Repository

About Ragflow Retrieval Mcp Server

Ragflow Retrieval Mcp Server connects MCP clients to RagFlow for content-based document retrieval from a knowledge base. It is intended for systems that need to search RagFlow datasets through MCP.

Key features

  1. 01Retrieve documents from RagFlow
  2. 02Search knowledge-base content
  3. 03Configure dataset and result count
  4. 04Set similarity threshold and timeout

Use cases

  1. 01Searching documents in a RagFlow dataset
  2. 02Retrieving knowledge-base content through an MCP client

MCP support

It exposes RagFlow content retrieval to MCP clients, using configured RagFlow connection and dataset settings.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ragflow-retrieval": {
      "command": "uvx",
      "args": [
        "ragflow-retrieval-mcp-server"
      ]
    }
  }
}
Run commanduvx ragflow-retrieval-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiragflow-retrieval-mcp-server

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

RAGFlow Retrieval MCP Server 🚀

Python Version License

该MCP Server用于对接RagFlow知识库系统，提供基于内容的文档检索能力。

前置要求
  • Python 3.10+
  • RagFlow
生产运行
export SERVER_HOST=http://localhost
export SERVER_PORT=80
export RAGFLOW_BASE_URL=http://localhost:80
export RAGFLOW_API_KEY=<your-api-key>
export RAGFLOW_DATASET_ID=<your-dataset-id>
export RAGFLOW_TOP_K=10
export RAGFLOW_SIMILARITY_THRESHOLD=0.2
export RAGFLOW_TIMEOUT=60

uvx ragflow-retrieval-mcp-server

开发调试

# 创建虚拟环境
uv venv
source .venv/bin/activate

# 安装依赖
uv pip install -e .

# 运行
uv run ragflow-retrieval-mcp-server

贡献指南 🤝

欢迎通过以下方式参与贡献：

  1. Fork仓库并创建特性分支
  2. 提交清晰的commit message
  3. 发起Pull Request并描述变更内容

请确保： ✅ 更新相关文档 ✅ 保持代码风格一致

许可证 📄

本项目采用 MIT License

遇到问题？ 请提交 Issue 或联系 [email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.