rag-agent-mcp

[](https://mseep.ai/app/shemhamforash23-lightrag-mcp) # RAG Agent RAG Agent is a CLI-enabled MCP server for integrating LightRAG Dataset functionality with AI tools. Provides a unified interface for managing datasets, querying data, and accessing knowledge graphs through the MCP protocol. Can be run directly via `uvx rag-agent`. ## Description RAG Agent is a specialized bridge between LightRAG's Dataset API and MCP-compatible clients. It enables dataset-isolated RAG operations, allowing you to create, manage, and query multiple independent datasets with their own knowledge graphs and document collections. ### Key Features - **Health Check**: Verify LightRAG API server status and configuration before operations - **Guided Workflow**: Built-in prompt to guide users through RAG operations step-by-step - **Dataset Management**: Create, update, delete, and list datasets with full configuration control - **Dataset Queries**: Execute queries on single or multiple datasets with cross-dataset reranking - **Document Management**: Upload, list, and delete documents within specific datasets - **Knowledge Graph Access**: Retrieve graph data and labels for dataset-specific knowledge graphs - **Dataset Isolation**: Each dataset maintains its own PostgreSQL schema for complete data separation ## Installation ### Quick Start with uvx (Recommended) ```bash # Run directly without installation uvx rag-agent --host localhost --port 9621 ``` ### Development Installation ```bash # Create a virtual environment uv venv --python 3.11 # Install the package in development mode uv pip install -e . ``` ## Requirements - Python 3.11+ - Running LightRAG API server ## Usage **Important**: RAG Agent should be run as an MCP server through an MCP client configuration file (mcp-config.json), or directly via `uvx rag-agent`. ### Command Line Options The following arguments are available w…