US EditionGoogle Launches Managed Remote MCP Servers for Its Cloud Services
Google's managed Model Context Protocol servers simplify AI agents' access to up-to-date tools and data with existing security controls, initially supporting Maps and BigQuery.
- At the TechCrunch event in San Francisco on October 13-15, 2026, Google launched fully managed, remote Model Context Protocol servers in public preview, offering the preview at no extra cost to enterprise customers.
- Because AI agents struggled to access external tools, developers previously had to patch together fragile connectors, so Google built the plumbing to ease integration challenges.
- At launch, the new servers cover Maps, BigQuery, Google Compute Engine and Google Kubernetes Engine and integrate with Apigee, Google Cloud IAM, Google Cloud Model Armor and audit logging.
- The change immediately reduces integration time, letting developers more easily build agents backed by Gemini 3 that access BigQuery and Maps, while Google expects general availability very soon in the new year with weekly MCP server additions.
- In the coming months, Google will publish available APIs in a Cloud API Registry and expand MCP support to services like Cloud Run, AlloyDB, and Security Operations tools.
11 Articles
11 Articles
Google Launches Managed Remote MCP Servers for Its Cloud Services
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 Googl…
Google launches managed MCP servers that let AI agents simply plug into its tools
Google is rolling out managed MCP servers to make its services “agent-ready by design,” starting with Maps and BigQuery, aiming to simplify messy integrations and help AI agents use real tools.
Google integrates the Model Context Protocol (MCP) developed by Anthropic directly into its cloud infrastructure. The article Google opens its infrastructure via MCP for AI models first appeared on The Decoder.
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
