How to build an AI Agent and MCP Server (step-by-step)

Опубликовано 18 июня 2026, 13:00

Follow the codelab here. → goo.gle/4vv5sx5
Github Repo → goo.gle/3RQR3g7
Google MCP servers → goo.gle/4xfafo8

Model Context Protocol (MCP) is the open standard *"universal adapter"* that empowers AI agents to overcome static training data by securely and uniformly connecting with the real world's live data and actionable tools. Join Smitha Kolan as she demonstrates how to connect external tools, such as Google Trends, using MCPs with AI agents. Watch along and unlock the power of Model Context Protocol (MCP) with Google's Agent Development Kit (ADK).

Chapters:
0:00 - Intro & What is Model Context Protocol (MCP)?
0:49 - How MCP works under the hood
2:41 - [Demo] Connecting Google Trends with a blog writing AI agent
6:22 - Running the agent in ADK Web UI
7:10 - Summary

More resources:
Google Cloud MCP servers docs → goo.gle/4oeVaPk
Manage MCP servers docs → goo.gle/3PLKtqG
Configure MCP in an AI application → goo.gle/4oab6lP

🔗 Connect with Smitha online:
YouTube → goo.gle/Smitha-on-YouTube
Linkedin → goo.gle/Smitha-on-LinkedIn
X → goo.gle/Smitha-on-X

Watch more Modern AI Agents: From Theory to Production → goo.gle/Learn-with-Smitha
🔔 Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#AIAgents #GoogleTrends

Speakers: Smitha Kolan
Products Mentioned: Agent Development Kit