Build and run Cognee MCP from source to unlock advanced customization, multiple transport options, and the latest development features. Local setup provides several advantages over the Docker quickstart:
  • Full Control: Customize server configuration, add custom providers, and modify behavior
  • Latest Features: Access bleeding-edge features from the development branch
  • Multiple Transports: Choose from stdio, SSE, or HTTP transport modes
  • Development Ready: Debug, modify, and contribute to the Cognee MCP codebase

​
Quick Setup

1

Clone Repository

git clone https://github.com/topoteretes/cognee.git
cd cognee
2

Environment Configuration

Create your .env file:
LLM_API_KEY="your-openai-api-key"
3

Install Dependencies

# Install uv package manager
brew install uv

# Install project dependencies
cd cognee-mcp
uv sync --dev --all-extras --reinstall
4

Activate & Run

# Activate virtual environment
source .venv/bin/activate

# Run with stdio transport (default)
python src/server.py

# Or run with SSE transport
python src/server.py --transport sse

​
Transport Options

Default transport mode for most MCP clients:
python src/server.py
If you encounter errors on first run, reset your MCP configuration and try again.

​
Need Help?

Join Our Community

Get support, share insights, and connect with other developers using Cognee MCP.