Ragflow Retrieval Mcp Server
About
This mcp server is used to search content from the ragflow knowledge base.
Details
- Author
- datahwc
- Downloads
- 240
- Categories
- Other
Jump to
- Connects to RAGFlow knowledge base systems.
- Provides content‑based document retrieval.
- Configurable retrieval parameters (top K, similarity threshold, timeout).
- Supports both production and development run modes.
- MIT licensed.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Ragflow Retrieval Mcp ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Set the required environment variables (SERVER_HOST, SERVER_PORT, RAGFLOW_BASE_URL, RAGFLOW_API_KEY, RAGFLOW_DATASET_ID, and optional RAGFLOW_TOP_K, RAGFLOW_SIMILARITY_THRESHOLD, RAGFLOW_TIMEOUT), then run uvx ragflow-retrieval-mcp-server. For development, create a virtual environment with uv venv, install dependencies with uv pip install -e ., and run with uv run ragflow-retrieval-mcp-server.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ragflow retrieval mcp server": {
"ragflow-retrieval-mcp-server": {
"command": "uvx",
"args": [
"ragflow-retrieval-mcp-server"
]
}
}
}
}McpServers
{
"ragflow-retrieval-mcp-server": {
"command": "uvx",
"args": [
"ragflow-retrieval-mcp-server"
]
}
}RAGFlow Retrieval MCP Server 🚀
[
[
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
```bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
