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 🧠

Python Version License Docker

🌟 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 (Model Context Protocol) 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:
git clone https://github.com/gifflet/graphiti-mcp-server.git
cd graphiti-mcp-server
  1. Set up environment variables:
cp .env.sample .env
  1. Edit .env with your configuration:
# Required for LLM operations
OPENAI_API_KEY=your_openai_api_key_here
MODEL_NAME=gpt-4o
  1. Start the services:
docker compose up

🔧 Configuration

Neo4j Settings 🗄️

Default configuration for Neo4j:

  • Username: neo4j
  • Password: demodemo
  • URI: bolt://neo4j:7687 (within Docker network)
  • Memory settings optimized for development

Docker Environment Variables 🐳

You can run with environment variables directly:

OPENAI_API_KEY=your_key MODEL_NAME=gpt-4o docker compose up

🔌 Integration

Cursor IDE Integration 🖥️

  1. Configure Cursor to connect to Graphiti:
{
  "mcpServers": {
    "Graphiti": {
      "url": "http://localhost:8000/sse"
    }
  }
}
  1. Add Graphiti rules to Cursor's User Rules (see graphiti_cursor_rules.md)
  2. Start an agent session in Cursor

🏗️ Architecture

The server consists of two main components:

  • Neo4j database for graph storage
  • Graphiti MCP server for API and LLM operations

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

  • Neo4j team for the amazing graph database
  • OpenAI for their powerful LLM models
  • MCP community for the protocol specification