Graphiti MCP Server • Fast Multi‑Project Knowledge Graphs
LocalAbout Graphiti MCP Server • Fast Multi‑Project Knowledge Graphs
Graphiti MCP Server is a fork of the Graphiti example for managing knowledge graphs. A CLI starts a root server and project-specific MCP servers in Docker, all sharing one Neo4j database. It targets developers who run several isolated graphs.
Key features
- 01Entity and relationship storage in Neo4j
- 02CLI generates compose file and starts services
- 03Per-project isolation using separate group_id values
- 04Ports written to .cursor/mcp.json automatically
- 05Hot reload of individual project configuration
Use cases
- 01Running several knowledge graphs on one Neo4j database
- 02Defining separate entities and extraction rules per project
- 03Letting editors discover MCP server ports automatically
MCP support
Each project container exposes an SSE endpoint at http://localhost:800{N}/sse for MCP-compatible tools to connect to.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGraphiti 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
- 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 - Launch services
The root server runs on port 8000; project containers start at 8001.graphiti compose # generates docker-compose.yml and updates .cursor/mcp.json graphiti up -d - Create a project
Reruncd /path/to/my-kg graphiti init my-kg # writes ai/graph/mcp-config.yaml # add entity definitions under ai/graph/entities/graphiti compose && graphiti up -dfrom 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:7474using 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
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.