RAGFlow MCP Server

A comprehensive Model Context Protocol (MCP) server for RAGFlow that provides full API access for semantic retrieval and knowledge base management.

Features

• Semantic Retrieval: Search across datasets using natural language queries
• Dataset Management: Create, list, update, and delete datasets
• Document Management: Upload, parse, list, download, and delete documents
• Chunk Management: Add, list, update, and delete document chunks
• Chat Assistants: Create and manage chat assistants with RAG capabilities
• Session Management: Create and manage chat sessions
• GraphRAG & RAPTOR: Build and query knowledge graphs (when supported by your RAGFlow instance)

Installation

Prerequisites

• Python 3.10+
• RAGFlow server running and accessible (v0.16.0+ for core features)
• RAGFlow API key

Note: GraphRAG and RAPTOR build APIs require RAGFlow v0.21.0 or later.

Install from source

git clone https://github.com/Juxsta/ragflow-mcp.git
cd ragflow-mcp
pip install -e .

Configure Claude Code

Add to your Claude Code MCP settings:

claude mcp add ragflow -e RAGFLOW_API_KEY=your-api-key -e RAGFLOW_URL=http://localhost:9380/api/v1 -- python -m src.server

Or manually add to ~/.claude/settings.json:

{
  "mcpServers": {
    "ragflow": {
      "command": "python",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/ragflow-mcp",
      "env": {
        "RAGFLOW_API_KEY": "your-api-key",
        "RAGFLOW_URL": "http://localhost:9380/api/v1"
      }
    }
  }
}

Environment Variables

Available Tools

Retrieval

• ragflow_retrieval_tool - Semantic search across datasets

Dataset Management

• ragflow_list_datasets_tool - List all datasets
• ragflow_create_dataset_tool - Create a new dataset
• ragflow_update_dataset_tool - Update dataset configuration
• ragflow_delete_dataset_tool - Delete a dataset (requires confirmation)

Document Management

• ragflow_list_documents_tool - List documents in a dataset
• ragflow_upload_document_tool - Upload a document (file path or base64)
• ragflow_parse_document_tool - Trigger async document parsing
• ragflow_parse_document_sync_tool - Parse and wait for completion
• ragflow_download_document_tool - Download document content
• ragflow_delete_document_tool - Delete a document (requires confirmation)
• ragflow_stop_parsing_tool - Cancel an active parsing job

Chunk Management

• ragflow_list_chunks_tool - List chunks in a document
• ragflow_add_chunk_tool - Add a chunk to a document