graphiti-mcp-server

graphiti-mcp-server

8
knowledge_and_memory

Graphiti MCP Server is a sophisticated knowledge graph server designed for AI agents, leveraging Neo4j and integrating seamlessly with Model Context Protocol. It supports dynamic knowledge management, advanced semantic search, and custom entity extraction, making it highly adaptable for various AI-driven applications.

Graphiti MCP Server 🧠

A powerful knowledge graph server for AI agents, built with Neo4j and integrated with Model Context Protocol (MCP).

🚀 Features

  • Dynamic knowledge graph management with Neo4j
  • Seamless integration with OpenAI models
  • MCP support
  • Docker-ready deployment
  • Custom entity extraction capabilities
  • Advanced semantic search functionality

🛠️ Installation

Prerequisites

  • Docker and Docker Compose
  • Python 3.10 or higher
  • OpenAI API key

Quick Start 🚀

  1. Clone the repository.
  2. Set up environment variables.
  3. Edit .env with your configuration.
  4. Start the services.

🔧 Configuration

Neo4j Settings

Default configuration for Neo4j with optimized memory settings for development.

Docker Environment Variables

Run with environment variables directly.

🔌 Integration

Cursor IDE Integration

  1. Configure Cursor to connect to Graphiti.
  2. Add Graphiti rules to Cursor's User Rules.
  3. Start an agent session in Cursor.

🏗️ Architecture

Consists of a Neo4j database for graph storage and Graphiti MCP server for API and LLM operations.

🤝 Contributing

Contributions are welcome! Please submit a Pull Request.

📝 License

Licensed under the MIT License.