Database Management stdio

Cognee

Name: Cognee
Author: topoteretes

Created by topoteretes

Provides a reliable memory layer for AI applications and AI agents, enhancing response accuracy and reducing hallucinations.

How to Connect & Install

Select your client or environment below to copy the verified, ready-to-run installation configuration.

1-line autonomous agent setup instruction. Paste into Claude Code, Codex CLI, or Cursor Agent:

Fetch and configure Model Context Protocol (MCP) server Cognee from https://www.fastmcp.dev/server/cognee

Agents automatically discover, install, and execute the server spec without manual token setup.

Connect via direct Stateless MCP v2 / Streamable HTTP endpoint or JSON-RPC:

https://github.com/topoteretes/cognee

Stateless edge endpoint compliant with MCP 2024-11-05 and v2 draft protocol specs.

Includes server instructions and tool definitions for Claude:

claude mcp add cognee -- npx -y cognee

Run in terminal to register server in current project or pass --scope user for global availability.

Configures server instructions and tools for OpenAI Codex & ChatGPT Desktop:

[mcp_servers.cognee]
command = "npx"
args = ["-y","cognee"]

Applies to ChatGPT Desktop app, Codex CLI, and IDE extension across your Codex host.

Add to Cursor project settings (.cursor/mcp.json) or Cursor Settings > Features > MCP:

{
  "mcpServers": {
    "cognee": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "cognee"
      ]
    }
  }
}

Commit to version control to allow teammates to connect immediately.

Install as an autonomous Agent Skill using the standard skills CLI:

npx skills add https://github.com/topoteretes/cognee

Standard agent skill installer compatible with Claude Code, Cursor, and agy harnesses.

Server Guidance & Instructions OpenAI & Claude Spec Compliant

Cognee: Provides a reliable memory layer for AI applications and AI agents, enhancing response accuracy and reducing hallucinations. Key capabilities: Reduces hallucinations, developer effort, and cost.; Manipulates data while ingesting from 30+ data sources.; Interconnects and retrieves past conversations, documents, images and audio transcriptions..

Codex and Claude read this instruction prompt during initialization to orchestrate cross-tool workflows and rate limits.

Top Core Functions

01 Reduces hallucinations, developer effort, and cost

02 Manipulates data while ingesting from 30+ data

03 Loads data to graph and vector databases