cognee-mcp

cognee MCP server

Installing Manually

A MCP server project

Clone the cognee repo
Install dependencies

brew install uv

cd cognee-mcp
uv sync --dev --all-extras --reinstall

Activate the venv with

source .venv/bin/activate

Add the new server to your Claude config:

The file should be located here: ~/Library/Application\ Support/Claude/

cd ~/Library/Application\ Support/Claude/

You need to create claude_desktop_config.json in this folder if it doesn't exist Make sure to add your paths and LLM API key to the file bellow Use your editor of choice, for example Nano:

nano claude_desktop_config.json

{
	"mcpServers": {
		"cognee": {
			"command": "/Users/{user}/cognee/.venv/bin/uv",
			"args": [
        "--directory",
        "/Users/{user}/cognee/cognee-mcp",
        "run",
        "cognee"
      ],
      "env": {
        "ENV": "local",
        "TOKENIZERS_PARALLELISM": "false",
        "LLM_API_KEY": "sk-"
      }
		}
	}
}

Restart your Claude desktop.

Installing via Smithery

To install Cognee for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install cognee --client claude

Define cognify tool in server.py Restart your Claude desktop.

To use debugger, run:

mcp dev src/server.py

Open inspector with timeout passed:

http://localhost:5173?timeout=120000

To apply new changes while developing cognee you need to do:

poetry lock in cognee folder
uv sync --dev --all-extras --reinstall
mcp dev src/server.py

Development

In order to use local cognee build, run in root of the cognee repo:

poetry build -o ./cognee-mcp/sources

After the build process is done, change the cognee library dependency inside the cognee-mcp/pyproject.toml from

cognee[postgres,codegraph,gemini,huggingface]==0.1.38

cognee[postgres,codegraph,gemini,huggingface]

After that add the following snippet to the same file (cognee-mcp/pyproject.toml).

[tool.uv.sources]
cognee = { path = "sources/cognee-0.1.38-py3-none-any.whl" }

Install Server

HTTP connection URL

security – no known vulnerabilities

license - permissive license

quality - confirmed to work

How are these scores calculated?

local-only server

The server can only run on the client's local machine because it depends on local resources.

Tools

Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources

Related MCP Servers

Memory Bank MCP
movibe
A
security
A
license
A
quality
Memory Bank Server provides a set of tools and resources for AI assistants to interact with Memory Banks. Memory Banks are structured repositories of information that help maintain context and track progress across multiple sessions.
Last updated -
15
111
13
TypeScript
MIT License
mem0 Memory System
pinkpixel-dev
A
security
A
license
A
quality
A flexible memory system for AI applications that supports multiple LLM providers and can be used either as an MCP server or as a direct library integration, enabling autonomous memory management without explicit commands.
Last updated -
3
88
54
JavaScript
MIT License
SourceSync.ai MCP Server
pbteja1998
-
security
A
license
-
quality
Allows AI models to interact with SourceSync.ai's knowledge management platform to organize, ingest, retrieve, and search content in knowledge bases.
Last updated -
14
1
TypeScript
MIT License
MCP Memory Server
sdimitrov
-
security
F
license
-
quality
Implements long-term memory capabilities for AI assistants using PostgreSQL with pgvector for efficient vector similarity search, enabling semantic retrieval of stored information.
Last updated -
1
JavaScript

View all related MCP servers

cognee-mcp

cognee MCP server

Installing Manually

A MCP server project

Installing via Smithery

Development

Tools

Related MCP Servers

Memory Bank MCP

mem0 Memory System

SourceSync.ai MCP Server

MCP Memory Server

Appeared in Searches

New MCP Servers

MCP directory API