Google Cloud Now Offers Official MCP Support Across Its Services to Power Agentic AI

Google Cloud has announced official support for the Model Context Protocol (MCP) across its portfolio of services, marking a major step in enabling AI agents to work reliably with real-world data, tools, and infrastructure.

MCP, an open standard originally developed by Anthropic, is often called “USB-C for AI” because it lets large language models connect to external tools and services in a consistent, secure way.

Recently, the Linux Foundation has announced the launch of the Agentic AI Foundation (AAIF), a new open governance body aimed at advancing open, interoperable, and community-driven development of agentic artificial intelligence.

Under the new rollout, Google is launching fully-managed, remote MCP servers that let developers point their AI agents, including clients like Gemini CLI and AI Studio, to a single enterprise-ready endpoint for Google and Google Cloud products. This removes the burden of installing and managing individual MCP servers, reducing complexity and improving reliability.

Initial MCP integration includes Google Maps, BigQuery, Google Compute Engine and Google Kubernetes Engine, giving agents access to geospatial data, enterprise analytics, autonomous infrastructure controls, and container management.

Google says it will expand support to additional services like Cloud Storage, AlloyDB, Cloud SQL, security operations, logging and more in the coming months.

“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,” said David Soria Parra, co-creator of MCP and member of technical staff at Anthropic. “As adoption grows among leading platforms, it brings us closer to agentic AI that works seamlessly across the tools and services people already use.”

The update also integrates with Apigee, enabling enterprises to expose internal APIs as discoverable tools for agents while maintaining governance via IAM controls and audit logging.

"We are bringing order to this ecosystem with a unified approach to discovery and governance. With the new Cloud API Registry and Apigee API Hub, developers can find trusted MCP tools from Google and their own organizations, respectively," Google said in a blog post.

As AI systems increasingly automate data-driven tasks, Google’s expanded MCP support aims to simplify agent integration and accelerate real-world adoption — empowering developers to build sophisticated, tool-connected AI applications with less complexity and greater control.