Google Announces Official MCP Support Across All Cloud Services

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

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

What This Means for Developers The release eliminates a critical pain point in agentic AI development. Previously, implementing Google's community-built MCP servers required developers to identify, install, and manage individual local servers—often leading to fragile implementations. With today's announcement, developers can simply point their AI agents or standard MCP clients like Gemini CLI and AI Studio to globally-consistent, enterprise-ready endpoints. "For AI to truly be an 'agent'—to pursue goals and solve real-world problems on behalf of users—it needs more than just intelligence; it needs to reliably work with tools and data," said Michael Bachman, VP/GM at Google Cloud. Enterprise Integration via Apigee Google is extending MCP capabilities to enterprise application stacks through Apigee. Customers can now expose and govern their own developer-built APIs, as well as external third-party APIs, as discoverable tools for AI agents. This enables organizations to leverage purpose-built APIs for specific data flows and business logic within agentic workflows. Built-in Security and Governance The announcement emphasizes enterprise-grade security with multiple layers of protection: The new Cloud API Registry and Apigee API Hub enable developers to find trusted MCP tools from Google and their own organizations. Administrators can manage access via Google Cloud IAM, rely on audit logging for observability, and utilize Google Cloud Model Armor to defend against advanced agentic threats including indirect prompt injection attacks. Anthropic Endorsement The announcement received immediate endorsement from Anthropic, the creator of MCP. David Soria Parra, co-creator of MCP and Member of Technical Staff at Anthropic, stated: "Google's support for MCP across such a diverse range of products, combined with their close collaboration on the specification, will help more developers build agentic AI applications. As adoption grows among leading platforms, it brings us closer to agentic AI that works seamlessly across the tools and services people already use." Upcoming MCP Rollout Google announced plans to roll out MCP support for additional services in coming months, including: Cloud Run, Cloud Storage, and Cloud Resource Manager for projects, compute, and storage. Database and analytics services including AlloyDB, Cloud SQL, Spanner, Looker, Pub/Sub, and Dataplex Universal Catalog are also on the roadmap. Security capabilities through Google Security Operations (SecOps), cloud operations via Cloud Logging and Cloud Monitoring, and additional Google services including Developer Knowledge API and Android Management API will follow. Agentic AI Foundation Membership Google confirmed its position as a founding member of the Agentic AI Foundation, committing to contribute to the evolution of MCP through the open source community. Anthropic recently announced it would donate the Model Context Protocol to the foundation to ensure vendor-neutral governance of the specification. Industry Implications Today's announcement signals a significant shift in enterprise AI infrastructure. With Google joining Microsoft, Anthropic, and other major players in supporting MCP, the protocol is rapidly becoming the de facto standard for AI agent tool integration. Gartner analysts have predicted that by 2027, 50% of enterprise AI deployments will utilize standardized tool protocols like MCP, up from less than 5% in 2024. Google's managed MCP servers could accelerate this timeline by removing infrastructure barriers for enterprise adoption. Getting Started Developers can access Google's MCP servers immediately through the official MCP documentation. A complete demo showcasing BigQuery and Maps integration via the Agent Development Kit (ADK) is available on GitHub.