Agent Evals by Galileo

The agent evals MCP by Galileo drives automatic self-improvements in your AI agents, and enables direct integration between Cursor and Galileo's agentic insights. With MCP, you can access Galileo's capabilities directly from your development environment, including: - Creating and managing datasets - Running experiments - Setting up prompt templates - Getting insights on Log streams - Integrating Galileo with your code

🛠️ Developer Tools Testing

Last updated: 1/27/2026

Installation

Add this MCP to your configuration:

{
  "mcpServers": {
    "galileo-ai": {
      // See GitHub repository for configuration
    }
  }
}