sciver

MCPOfficialCognee

Cognee MCP

Long-term agent memory built on a knowledge graph: remember, recall and forget.

The MCP server for Cognee exposes agent memory through three tools – remember, recall and forget – storing data in a knowledge graph, while code_search queries indexed code (symbols, dependencies and architecture). It runs locally over stdio, SSE or HTTP or connects to Cognee Cloud; the default setup needs an LLM key, such as OpenAI.

Installation

Manual install

$docker run -e TRANSPORT_MODE=http --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main

Details

Works in
Claude Code, Claude, Cursor, Codex, Gemini CLI, VS Code, Windsurf, Zed
Transport
local
License
Apache-2.0
Tasks
Research, Code
Rating
Source
github.com/topoteretes/cognee/tree/main/cognee-mcp (opens in a new tab)

Tags

  • memory
  • knowledge graph
  • rag
  • agents

Log in to rate

A pack is your own set of skills and MCP servers. sciver loads it in your AI with one command.

View in the library