mcpserver.so LogoMCPFly
Submit
Graphiti MCP Server logo

Graphiti MCP Server

by gifflet

Knowledge ManagementNeo4jKnowledge GraphAI AgentsDocker

Graphiti MCP Server is a powerful knowledge graph server designed for AI agents. It is built with Neo4j and integrates with the Model Context Protocol (MCP).

View on GitHub

Last updated: N/A

What is Graphiti MCP Server?

Graphiti MCP Server is a knowledge graph server that leverages Neo4j for graph storage and implements the Model Context Protocol (MCP) to facilitate seamless integration with AI models, particularly OpenAI's LLMs. It provides a robust platform for managing and querying knowledge graphs within AI-driven applications.

How to use Graphiti MCP Server?

To use Graphiti MCP Server, first clone the repository, set up environment variables (including your OpenAI API key), and then start the services using Docker Compose. Configure your AI agent or application (e.g., Cursor IDE) to connect to the server's API endpoint. You can then interact with the knowledge graph through the server's API.

Key features of Graphiti MCP Server

  • 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

Use cases of Graphiti MCP Server

  • Building AI agents with contextual awareness

  • Enhancing LLM performance with knowledge graphs

  • Developing semantic search applications

  • Creating knowledge-driven chatbots

  • Implementing advanced data integration solutions

FAQ from Graphiti MCP Server

What is Neo4j?

Neo4j is a graph database management system.

What is MCP?

MCP stands for Model Context Protocol, a standard for exchanging context between AI models.

How do I configure the OpenAI API key?

Set the OPENAI_API_KEY environment variable in the .env file.

What is the default Neo4j username and password?

The default username is 'neo4j' and the password is 'demodemo'.

How do I contribute to the project?

Submit a Pull Request with your proposed changes.