This is a MCP server I built to interact with my hybrid graph rag db.
Overview
What is GraphRAG MCP Server?
GraphRAG MCP Server is a Model Context Protocol server designed for querying a hybrid graph and vector database system, integrating Neo4j and Qdrant for enhanced semantic and graph-based document retrieval.
How to use GraphRAG MCP Server?
To use the server, clone the repository, install dependencies, configure your database connections in the .env file, and run the server using the provided commands.
Key features of GraphRAG MCP Server?
- Semantic search using sentence embeddings and Qdrant.
- Graph-based context expansion utilizing Neo4j.
- Hybrid search that combines vector similarity with graph relationships.
- Full integration with LLMs through the Model Context Protocol.
Use cases of GraphRAG MCP Server?
- Enhancing document retrieval in applications requiring semantic understanding.
- Enabling complex queries that leverage both graph and vector data.
- Supporting AI applications that require context-aware information retrieval.
FAQ from GraphRAG MCP Server?
- Can I use this server with any MCP-enabled client?
Yes! The server is compatible with any client that follows the Model Context Protocol.
- What databases are required to run this server?
You need Neo4j and Qdrant running on your local machine.
- Is there documentation available for setup?
Yes, detailed setup guides and documentation are provided in the repository.