Graphiti exposes a knowledge graph server for AI agents, built on Neo4j. It provides tools for querying, updating, and managing graph data. The server connects to Neo4j databases and integrates with MCP for agent interaction. Developers use it for building AI applications that require graph-based data processing and semantic querying.
Graphiti exposes a knowledge graph server for AI agents, built on Neo4j. It provides tools for querying, updating, and managing graph data. The server connects to Neo4j databases and integrates with MCP for agent interaction. Developers use it for building AI applications that require graph-based data processing and semantic querying.
pip install graphiti-mcp-serverAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"gifflet-graphiti-mcp-server-github": {
"command": "uvx",
"args": [
"pip install graphiti-mcp-server"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from graphiti?"
API Key Required
This server requires an API key from graphiti. Add it to your environment or config.
| Variable | Required | Description |
|---|---|---|
| GRAPHITI_API_KEY | Yes | Your graphiti API key |
"What resources are available in graphiti?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in graphiti"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in graphiti with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.