Cognee MCP brings persistent AI memory to your AI-powered workflow through the Model Context Protocol (MCP).

​
What is MCP?

The Model Context Protocol (MCP) is a standard for adding specialized tools to AI assistants. It allows assistants such as Claude or Cursor to work with external systems like databases, APIs, and AI systems (like Cognee). Without MCP, each assistant would need its own custom way to support the specialized tools, and each system would need separate implementations for every assistant. This leads to duplication and inconsistency. MCP offers a single, secure method for extending assistants, with:
  • Standardized connections between AI tools and external systems
  • Secure data access with built-in authentication and permissions
  • Tool interoperability so you can switch between different AI providers
  • Persistent memory that survives across conversations and sessions

​
How Cognee MCP Works

Cognee MCP works by exposing 11 specialized tools through the MCP protocol. These tools handle memory management, code intelligence, and data operations. You use these tools through MCP-compatible AI assistants like Cursor, Claude Desktop, Continue, Cline, and Roo Code. The tools enable your AI assistant to:
  • Store and retrieve knowledge from previous conversations
  • Build persistent understanding of your codebase and projects
  • Access structured memories across different sessions
See the Tools Reference for a complete list of available operations.

​
Setup Options

Choose your preferred deployment method:

Docker Quickstart

Recommended for most usersGet running in minutes with a ready-to-use container.

Local Setup

For developers & customizationBuild from source for full control and latest features.

​
Next Steps

Tools Reference

Complete reference for all available MCP tools and operations

Client Integrations

Connect with Cursor, Claude, Continue, and more