Graphiti MCP Server • Fast Multi‑Project Knowledge Graphs
About
Graphiti Model Context Protocol (MCP) Server - An MCP server for knowledge graph management via Graphiti
Details
- Author
- rawr-ai
- GitHub stars
- 100
- Downloads
- 573
- Categories
- Knowledge Base
Jump to
- Multi-project knowledge graphs sharing one Neo4j database
- Project isolation with different extraction rules per project
- Editor auto-discovery via .cursor/mcp.json port writing
- Crash containment — a bad prompt restarts only its container
- Hot reload for individual project configs
- Root server status endpoint at /graphiti/status
Install with pipx, clone the repo, and fill in Neo4j credentials and OpenAI key in .env. Run graphiti compose to generate Docker config, then graphiti up -d to launch. Create projects with graphiti init <name> and add entity definitions. Connect MCP-compatible tools to the SSE endpoint at http://localhost:800{N}/sse.
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
IfNEO4J_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 owngroup_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
SettingNEO4J_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
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.


