🔗 Official Repository

Always check the official repository for the latest setup instructions and license.

What is it?

Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources. — is a Model Context Protocol (MCP) server enabling AI applications like Claude and Cursor to securely access knowledge and memory capabilities through the open protocol.

Common Use Cases

Connect Claude or Cursor directly to knowledge and memory
Automating repetitive tasks through AI agents
Building smart workflows combining multiple tools in one pipeline

Quick Install (Claude Desktop)

{
  "mcpServers": {
    "cognee": {
      "command": "npx",
      "args": ["-y", "topoteretes/cognee"]
    }
  }
}

Add to your Claude Desktop config file after installing requirements per the repo instructions.

Similar Servers

apecloud/ApeRAG

Production-ready RAG platform combining Graph RAG, vector search, and full-text search. Best choice for building your own Knowledge Graph and for Context Engi

ANG 65/100

bitbonsai/mcpvault

Universal AI bridge for Obsidian vaults using MCP. Provides safe read/write access to notes with 11 comprehensive methods for vault operations including searc

ANG 65/100

chopratejas/headroom

Context compression layer for AI agents. Compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach the LLM, with reversible

ANG 65/100

entanglr/zettelkasten-mcp

A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, and search atomic notes

ANG 65/100

lostintangent/gistpad-mcp

Use GitHub Gists to manage and access your personal knowledge, daily notes, and reusable prompts. This acts as a companion to https://gistpad.dev and the Gist

ANG 65/100

graphlit/graphlit-mcp-server

Ingest anything from Slack, Discord, websites, Google Drive, Linear or GitHub into a Graphlit project - and then search and retrieve relevant knowledge within

ANG 65/100