Getting Started

Install Cerebro and connect it to your MCP client in under 2 minutes.

1Prerequisites

  • Python 3.10+

    Check with python --version

  • pip

    Usually included with Python. Check with pip --version

2Installation

Install Cerebro from PyPI with a single command:

terminal
pip install cerebro-ai

3Initialize

Run the init command to set up your storage directory and default configuration:

terminal
cerebro init

This creates the default storage at ~/.cerebro/data with the memory database, embeddings index, and directory structure.

4Configure Your MCP Client

Add Cerebro to your MCP client configuration. Here is the JSON snippet for Claude Desktop:

~/.claude/mcp.json (Claude Code)
{
  "mcpServers": {
    "cerebro": {
      "command": "cerebro",
      "args": ["serve"]
    }
  }
}

Config file locations:

  • Claude Code (CLI): ~/.claude/mcp.json
  • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
  • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
  • Claude Desktop (Linux): ~/.config/Claude/claude_desktop_config.json

5Verify Installation

Confirm everything is working:

terminal
cerebro doctor

You should see a status report showing your storage path, memory count, FAISS index health, and platform info.

Next Steps