 |
VOOZH | about |
|
VOOZH | about |
We’re so glad you’re here. You can expect all the best TNS content to arrive Monday through Friday to keep you on top of the news and at the top of your game.
Check your inbox for a confirmation email where you can adjust your preferences and even join additional groups.
Follow TNS on your favorite social media networks.
Become a TNS follower on LinkedIn.
Check out the latest featured and trending stories while you wait for your first TNS newsletter.
Model Context Protocol (MCP) has become the de facto standard for large language models (LLMs) to interact with third-party services, and to enable this, those third-party services must offer an MCP server that the LLM can connect to. At this point, even as MCP has barely turned a year old, virtually every online service features an MCP server.
Today, Google is extending its MCP support by offering fully managed MCP servers for many of its Google and Google Cloud services — with many more to come.
Until now, developers had to use Google’s community-built local servers or deploy open source solutions, which, as Google notes, were often difficult to install and manage. By offering these new managed MCP servers, Google is removing all of this additional work, making it far easier for a developer to build an agent that is backed by Google’s new Gemini 3 model, for example, and that connects to both the BigQuery data service and Google Maps to enrich this data with geospatial information.
“With these new and extended MCP capabilities, we are ensuring developers and agents can easily interact with data and take actions too. Google is committed to leading the AI revolution not just by building the best models, but also by building the best ecosystem for those models and agents to thrive,” Michael Bachman, Google’s VP and GM of Google Cloud, and Anna Berenberg, Google Cloud engineering fellow, write in today’s announcement.
BigQuery and Maps are among the first services to get the new managed MCP servers, together with the Google Compute Engine (GCE), which will allow agents to manage infrastructure workflows and provision and resize instances, for example, as well as the Google Kubernetes Engine (GKE), which will offer a server that allows agents to work with the Kubernetes and GKE APIs.
Here are the other services that will also get MCP support in the coming months:
To discover, govern, use and monitor these services, Google is using the Cloud API Registry, which is still in preview. The Registry will provide all the details of which APIs and tools are available for the agents to use (and which features of these APIs they can access).
Today’s announcement comes a day after Anthropic donated the MCP protocol specs to the Linux Foundation as part of the new vendor-neutral Agentic AI Foundation (AAIF).
“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, a 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.”
Google’s Apigee API management service is also getting extended MCP support, allowing enterprises to manage their custom MCP servers and how agents access them from the same tool they already use to manage their APIs.
