Discover how to combine the power of the Agent Development Kit (ADK) and Cloud Run to build scalable, production-ready AI agents. In this session, we’ll explore a hands-on example where an AI “tour guide” agent interacts with a Model Context Protocol (MCP) server that delivers zoo animal data. You’ll learn how to separate reasoning from tooling by hosting the MCP server on Cloud Run and integrating it with an ADK-powered agent for secure, efficient communication.

By the end of this session, you’ll understand:
• How to design and deploy an MCP server on Cloud Run.
• How to connect ADK agents with remote tools for dynamic data retrieval.
• Best practices for building scalable, cost-efficient AI agents ready for production environments.

Whether you’re an AI developer or a cloud architect, this session will help you accelerate your journey to building real-world, agentic AI solutions with Google Cloud.

• First Delivery: Part of Google’s Accelerate AI with Cloud Run program.
• Technical Level: Intermediate – familiarity with Python/Node.js
• Target Audience: AI developers, cloud architects, and solution engineers exploring agentic AI solutions.
• Duration: 45–60 minutes (including demo and Q&A).