图形化知识
HTTP-SSE基于MCP协议的多项目时序知识图谱服务器
基于MCP协议的多项目时序知识图谱服务器
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.
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
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
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 -d from anywhere to start its container.Once running you can:
http://localhost:8000/graphiti/status.http://localhost:800{N}/sse.http://localhost:7474 using the credentials in .env.If NEO4J_PASSWORD remains password the server refuses to start unless GRAPHITI_ENV=dev. Always use a strong password in production.
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.
.cursor/mcp.json.graphiti reload <container>.Leave mcp-projects.yaml empty if you only need the root server.
Setting NEO4J_DESTROY_ENTIRE_GRAPH=true wipes all projects the next time you run graphiti up. Use with care.
PRs and issues are welcome.
© 2025 rawr‑ai • MIT License