cognee-mcp-server

What is cognee-mcp-server?

cognee-mcp-server is an MCP server for cognee, an AI memory engine. It provides a tool that builds a knowledge graph from input text and performs search within that graph, intended for developers integrating memory capabilities into AI assistants.

How to use cognee-mcp-server?

Install with uv (Python package manager) and configure in Claude Desktop by adding an entry to claude_desktop_config.json using uvx. Invoke the Cognify_and_search tool with required inputs text and search_query, and optional graph_model_file and graph_model_name for a custom Pydantic graph model.

Key features of cognee-mcp-server

• Builds knowledge graphs from input text
• Performs search within constructed knowledge graphs
• Supports custom Pydantic graph models
• Configurable with Claude Desktop via uvx
• Uses multiple database providers (NetworkX, LanceDB, SQLite)

Use cases of cognee-mcp-server

• Semantic search over user-provided text data
• Queryable memory for AI assistants
• Knowledge graph retrieval from custom content

FAQ from cognee-mcp-server

What tool does cognee-mcp-server provide?

It provides the Cognify_and_search tool that builds a knowledge graph from input text and performs search in it, returning retrieved edges of the graph.

How do I configure cognee-mcp-server for Claude Desktop?

Add a configuration entry to claude_desktop_config.json using the uv command with the --directory flag pointing to the server path, and set required environment variables such as LLM_API_KEY, GRAPH_DATABASE_PROVIDER, VECTOR_DB_PROVIDER, DB_PROVIDER, and DB_NAME.

What are the required environment variables?

Required environment variables include ENV, TOKENIZERS_PARALLELISM, LLM_API_KEY, GRAPH_DATABASE_PROVIDER (e.g., networkx), VECTOR_DB_PROVIDER (e.g., lancedb), DB_PROVIDER (e.g., sqlite), and DB_NAME (e.g., cognee_db).

Can I use a custom graph model?

Yes, you can provide optional graph_model_file (filename of a custom Pydantic graph model implementation) and graph_model_name (class name) to customize the graph model.

What output does the Cognify_and_search tool produce?

The tool returns the retrieved edges of the knowledge graph as output.