What is Google MCP support?

Google has released fully-managed, remote Model Context Protocol (MCP) servers that enable AI agents to connect with Google Cloud services like Maps, BigQuery, GCE, and GKE. MCP is an open standard created by Anthropic that acts as USB-C for AI—providing a unified way for AI models to work with tools and data.

Which Google services support MCP?

Initial MCP support includes Google Maps (Grounding Lite API), BigQuery (schema interpretation and queries), Google Compute Engine (infrastructure provisioning), and Google Kubernetes Engine (container operations). Additional services including Cloud Run, AlloyDB, Cloud SQL, Spanner, and Looker are coming soon.

How does Google MCP differ from community servers?

Unlike community-built MCP servers that require developers to identify, install, and manage individual local servers, Google's managed MCP servers provide globally-consistent, enterprise-ready endpoints with built-in security via IAM, audit logging, and Model Armor protection against prompt injection.

What is the Agentic AI Foundation?

The Agentic AI Foundation is a new organization ensuring vendor-neutral governance of the Model Context Protocol. Google is a founding member alongside Anthropic, which donated MCP to the foundation. The organization will guide the evolution of MCP through the open source community.

How can developers start using Google MCP?

Developers can access Google MCP servers immediately through the official documentation at docs.cloud.google.com/mcp. AI agents and MCP clients like Gemini CLI and AI Studio can connect to globally-consistent endpoints. A demo using Agent Development Kit (ADK) is available on GitHub.

Google Announces Official MCP Support Across All Cloud Services

Google Cloud unveils fully-managed Model Context Protocol (MCP) servers for Google Maps, BigQuery, GKE, and GCE, enabling AI agents to seamlessly connect with enterprise data and infrastructure.

Published: December 10, 2025 By Marcus Rodriguez Category: Agentic AI

BREAKING: Google Announces Official MCP Support Across All Cloud Services

Mountain View, CA — December 10, 2025 — In a major development for the agentic AI ecosystem, Google Cloud has announced the release of fully-managed, remote Model Context Protocol (MCP) servers across its entire service portfolio. The announcement, made by VP/GM Michael Bachman and Engineering Fellow Anna Berenberg, positions Google as a leading contributor to the emerging standard that Anthropic has dubbed "USB-C for AI."

Executive Summary

Google's existing API infrastructure is now enhanced to support MCP, providing a unified layer across all Google and Google Cloud services. The announcement comes alongside the launch of Gemini 3, Google's most advanced reasoning model. Anthropic, creator of the Model Context Protocol, endorsed the move, with MCP co-creator David Soria Parra stating that Google's support "will help more developers build agentic AI applications."

Initial MCP Server Rollout

...

Read the full article at AI BUSINESS 2.0 NEWS

Service	MCP Capability	Use Case
Google Maps	Grounding Lite API	Real-world location queries, weather, routing
BigQuery	Schema interpretation, query execution	Enterprise data reasoning without data movement
Google Compute Engine	Provisioning, resizing as tools	Autonomous infrastructure management
Google Kubernetes Engine	Kubernetes API interface	Container operations, issue diagnosis, cost optimization