mcpField
G
Graphiti MCP Server

Graphiti MCP Server

Local
github.com/mateicanavraMemory & Knowledge102Updated 66w ago
Repository

About Graphiti MCP Server

Graphiti MCP Server is a fork of the getzep/graphiti example for managing knowledge graphs through Graphiti. It extracts entities and relationships from text into Neo4j and adds a CLI that starts a root server plus project-specific MCP servers in Docker, so several graphs share one database. It targets developers working on multiple projects.

Key features

  1. 01CLI for managing root and project servers
  2. 02Multiple project graphs sharing one Neo4j database
  3. 03Per-project group_id, entities and models
  4. 04Hot reload of project configuration
  5. 05Crash containment per project container

Use cases

  1. 01Maintaining separate knowledge graphs for several projects
  2. 02Connecting editors to each project's graph server over MCP
  3. 03Running several graph services on a single database

MCP support

The project provides MCP servers reachable over SSE endpoints such as http://localhost:800{N}/sse, and writes their ports to .cursor/mcp.json for editor auto-discovery.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Graphiti MCP Server

Fork of the getzep/graphiti example with a focus on developer experience and multi‑project support. Graphiti extracts entities and relationships from text and stores them in Neo4j. This repo adds a CLI that spins up a root server plus project‑specific MCP servers in Docker so several knowledge graphs share the same database.

Quick Start

  1. Install and clone 
    pipx install 'git+https://github.com/rawr-ai/mcp-graphiti.git'
git clone https://github.com/rawr-ai/mcp-graphiti.git
cd mcp-graphiti
cp .env.example .env  # fill in Neo4j credentials and your OpenAI key
  2. Launch services 
    graphiti compose   # generates docker-compose.yml and updates .cursor/mcp.json
graphiti up -d
    The root server runs on port 8000; project containers start at 8001.
  3. Create a project 
    cd /path/to/my-kg
graphiti init my-kg        # writes ai/graph/mcp-config.yaml
# add entity definitions under ai/graph/entities/
    Rerun graphiti compose && graphiti up -d from anywhere to start its container.

Once running you can:

  • Check http://localhost:8000/graphiti/status.
  • Connect MCP‑compatible tools to http://localhost:800{N}/sse.
  • Browse Neo4j at http://localhost:7474 using the credentials in .env.
Security note

If NEO4J_PASSWORD remains password the server refuses to start unless GRAPHITI_ENV=dev. Always use a strong password in production.

Why this fork?

The upstream repository assumes one server per compose file. Here a single compose file manages many project servers that share Neo4j. Each service gets its own group_id, entities and model so projects stay isolated while running on the same database.

Highlights
  • Project isolation – different extraction rules or models never collide.
  • Editor auto‑discovery – ports are written to .cursor/mcp.json.
  • Crash containment – a bad prompt only restarts its container.
  • Hot reload – tweak a project's config and run graphiti reload <container>.

Leave mcp-projects.yaml empty if you only need the root server.

Danger zone

Setting NEO4J_DESTROY_ENTIRE_GRAPH=true wipes all projects the next time you run graphiti up. Use with care.

Contributing

PRs and issues are welcome.

© 2025 rawr‑ai • MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.