MCP.so
Sign In
R

Ragflow Retrieval MCP Server

@datahwc

Basic information

Category

Other

Transports

stdio

Author

datahwc

Submitted by

datahwc

About Ragflow Retrieval MCP Server

This mcp server is used to search content from the ragflow knowledge base.

Ragflow Retrieval MCP Server config

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

{
  "mcpServers": {
    "ragflow-retrieval-mcp-server": {
      "command": "uvx",
      "args": [
        "ragflow-retrieval-mcp-server"
      ]
    }
  }
}

Ragflow Retrieval MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Ragflow Retrieval Mcp Server?

Ragflow Retrieval Mcp Server is an MCP (Model Context Protocol) server that integrates with the RAGFlow knowledge base system to provide content‑based document retrieval capabilities.

How to use Ragflow Retrieval Mcp Server?

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.

Key features of Ragflow Retrieval Mcp Server

  • 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.

Use cases of Ragflow Retrieval Mcp Server

—

Frequently asked questions

1

What are the runtime requirements?

Python 3.10 or higher and a running RAGFlow instance.

2

How do I configure the server?

Set the environment variables `RAGFLOW_BASE_URL`, `RAGFLOW_API_KEY`, and `RAGFLOW_DATASET_ID`. Optionally set `RAGFLOW_TOP_K` (default 10), `RAGFLOW_SIMILARITY_THRESHOLD` (default 0.2), and `RAGFLOW_TIMEOUT` (default 60).

3

Where does the data live?

Data is stored in the connected RAGFlow knowledge base; the server only retrieves results.

Comments

More Other MCP servers