Google has announced official support for the Model Context Protocol across its major services and Google Cloud products. The company said these managed remote servers will make it easier for developers to connect AI agents, including those powered by Gemini or other models, to real world tools, data sources and enterprise systems. This will also help enterprises link their AI agents to a wide range of third party data systems. Google added that the support will roll out to all of its services in stages.
In the first phase, Google Maps, BigQuery, Google Compute Engine and Google Kubernetes Engine will support MCP servers. With this, AI agents can call these platforms and access data with permissions to perform tasks in real scenarios. The company shared that a BigQuery MCP server will let an agent interpret table schemas, run queries directly on enterprise data and get insights without moving the data into the AI system. The MCP server for Maps will offer real world location information such as weather, routes and points of interest, helping agents answer travel planning questions with accurate and updated data.
Google is also extending MCP support to Apigee, its API management platform used by many enterprises to manage internal data and workflows. This update will let organisations turn their existing APIs into MCP compatible tools without rewriting them. It means AI agents can use a company’s own systems including customer databases, workflow systems and business logic as if they were native MCP tools, while still maintaining enterprise security and governance controls.
To address security, Google said it has added several layers of protection to safeguard these servers from cyberattacks. Enterprises can manage access through Google Cloud Identity and Access Management, use audit logging to track agent activity and apply “Model Armor” protection to reduce risks such as indirect prompt injection.
MCP is an open standard created by Anthropic and is often referred to as something like a USB C port for AI. It defines a common way for AI models and applications to connect to data systems, APIs and services. Earlier developers had to build custom connectors for each API or data source, which took time and often created fragile systems. With MCP, AI clients such as Gemini CLI and AI Studio can call a remote MCP server to discover, authenticate and use external resources in a standard manner.
Before this announcement, Google’s MCP support depended mainly on community built servers or open source tools that developers had to install and manage. With the new managed MCP servers, Google now handles the heavy setup so developers can let their Gemini powered agents connect to a consistent, enterprise ready endpoint for Google and Google Cloud services.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream formerly known as CIO News LinkedIn Account | The Mainstream formerly known as CIO News Facebook | The Mainstream formerly known as CIO News Youtube | The Mainstream formerly known as CIO News Twitter
About us:
The Mainstream is a premier platform delivering the latest updates and informed perspectives across the technology business and cyber landscape. Built on research-driven, thought leadership and original intellectual property, The Mainstream also curates summits & conferences that convene decision makers to explore how technology reshapes industries and leadership. With a growing presence in India and globally across the Middle East, Africa, ASEAN, the USA, the UK and Australia, The Mainstream carries a vision to bring the latest happenings and insights to 8.2 billion people and to place technology at the centre of conversation for leaders navigating the future.
