Graphiti MCP Server • Fast Multi‑Project Knowledge Graphs

what is Graphiti MCP Server?

Graphiti MCP Server is a server designed for managing knowledge graphs using the Graphiti Model Context Protocol (MCP). It enables AI agents to interact with knowledge graphs for persistent memory, entity extraction, and relationship tracking.

how to use Graphiti MCP Server?

To use the Graphiti MCP Server, you need to install the graphiti CLI tool, set up the necessary environment, and run the server using Docker. You can initialize projects, manage entities, and control the Docker environment through the CLI.

key features of Graphiti MCP Server?

• Exposes Graphiti functionality via MCP (SSE or Stdio transport).
• Provides tools for adding/searching episodes, nodes, and facts in a knowledge graph.
• Supports custom entity definitions for tailored extraction.
• Includes a CLI for project initialization, entity management, and Docker environment control.
• Uses Docker Compose for easy deployment of the MCP server(s) and Neo4j database.

use cases of Graphiti MCP Server?

1. Managing and querying knowledge graphs for AI applications.
2. Extracting and tracking entities and relationships in various domains.
3. Facilitating persistent memory for AI agents.

FAQ from Graphiti MCP Server?

• What are the prerequisites for using Graphiti MCP Server?

You need Python 3.10 or higher, Docker, Docker Compose, and the uv package.

• How do I install the graphiti CLI?

You can install it globally using pipx or set up a local development environment using venv.

• Can I run the server without Docker?

Yes, you can run the server directly for debugging, but Docker is recommended for deployment.