Topoteretes Cognee MCP Server

🚀 Tools

• Cognify_and_search: Build a knowledge graph from the input text and perform searches within it.
  • Input:
    • text (string): Context for building the knowledge graph.
    • search_query (string): Retrieval query.
    • graph_model_file (string, optional): Filename of the custom pydantic graph model implementation.
    • graph_model_name (string, optional): Class name of the custom pydantic graph model implementation.
  • Output:
    • Edges retrieved from the knowledge graph.

📦 Installation

Using Claude Desktop

Install uv using Homebrew.

Add the following content to your claude_desktop_config.json:

"mcpcognee": {
  "command": "uv",
  "args": [
    "--directory",
    "/path/to/your/cognee-mcp-server",
    "run",
    "mcpcognee"
  ],
  "env": {
    "ENV": "local",
    "TOKENIZERS_PARALLELISM": "false",
    "LLM_API_KEY": "your llm api key",
    "GRAPH_DATABASE_PROVIDER": "networkx",
    "VECTOR_DB_PROVIDER": "lancedb",
    "DB_PROVIDER": "sqlite",
    "DB_NAME": "cognee_db"
  }
}