Graphiti MCP Server
by mateicanavra
The Graphiti MCP Server allows AI agents to interact with a knowledge graph for persistent memory, entity extraction, and relationship tracking using the Graphiti framework. It includes a command-line interface (CLI) tool for project management and deployment.
Last updated: N/A
What is Graphiti MCP Server?
The Graphiti MCP Server is a server that exposes Graphiti functionality via the Model Context Protocol (MCP). It provides a persistent memory solution for AI agents by allowing them to interact with a knowledge graph.
How to use Graphiti MCP Server?
To use the Graphiti MCP Server, you need to install the graphiti CLI using either pipx (recommended for users) or venv (for developers). Then, you can use the CLI to initialize projects, manage entities, and run the Docker services that include the MCP server and Neo4j database. The CLI provides commands for generating Docker Compose configurations, starting and stopping services, and checking the setup.
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 type definitions for tailored extraction
Includes a CLI (
graphiti) for project initialization, entity management, and Docker environment controlUses Docker Compose for easy deployment of the MCP server(s) and Neo4j database
Leverages
uvfor fast dependency management
Use cases of Graphiti MCP Server
Persistent memory for AI agents
Entity extraction from text or other data sources
Relationship tracking between entities
Knowledge graph management and querying
FAQ from Graphiti MCP Server
How do I install the Graphiti CLI?
How do I install the Graphiti CLI?
It is recommended to install the CLI globally using pipx for managing projects and running services. Alternatively, developers can set up a local development environment using venv.
What are the prerequisites for running the server?
What are the prerequisites for running the server?
You need Python 3.10 or higher, Docker & Docker Compose, and uv installed.
How do I start the server?
How do I start the server?
The server runs as a Docker container managed by Docker Compose. Use the graphiti up command from the repository root to start the services.
How do I update the CLI after pulling changes from the repository?
How do I update the CLI after pulling changes from the repository?
Navigate back to the repository root, pull the latest changes, and then upgrade the pipx installation using pipx upgrade rawr-mcp-graphiti.
What does the graphiti check-setup command do?
What does the graphiti check-setup command do?
This command checks if the repository root is found, the .env file exists, and Docker is running.