Google LLC today introduced managed MCP servers that will enable artificial intelligence agents to interact with four of its cloud services. 

Until recently, giving AI agents access to an application required manually building an integration between the two workloads. That task can take a significant amount of time. It also increases the amount of bespoke code in software projects, which raises the risk of bugs.

MCP is an open-source technology that addresses the challenge. It enables developers to create an agent-friendly interface called an MCP server for an application. When third parties wish to connect their AI agents to the application, they can use the ready-made MCP server instead of building a custom integration.

MCP speeds up development, but using it in production involves certain challenges. Developers have to set up infrastructure on which their application’s MCP server can run and then maintain it. The managed MCP servers that Google debuted today are designed to ease those tasks for its customers. They remove the need to set up or maintain the underlying infrastructure.

The MCP servers support four Google Cloud services: Google Maps Platform, BigQuery, Google Compute Engine and GKE.

Google Maps Platform is the developer version of the company’s popular mapping platform. The accompanying MCP server is called Maps Grounding Lite and enables AI agents to access data from the service. A navigation app, for example, could use it to help drivers find the fastest route to a destination.

The second new MCP server enables AI agents to query records stored in BigQuery. The integration lends itself to, among other tasks, generating forecasts such as revenue predictions. According to Google, the MCP server enables AI agents to access BigQuery data without loading it into their context windows. That avoids the cybersecurity risks associated with moving business information to a new environment. 

The two other new MCP servers will help companies manage their Google Cloud environments. The first allows AI agents to perform tasks such as provisioning Google Compute Engine instances. The second MCP server gives AI agents access to Google Cloud’s GKE managed Kubernetes service. 

“The GKE MCP server exposes a structured, discoverable interface that allows agents to interact reliably with both GKE and Kubernetes APIs,” Google executives Michael Bachman and Anna Berenberg wrote in a blog post. “This unified surface allows agents, operating autonomously or with human-in-the-loop guardrails, to diagnose issues, remediate failures, and optimize costs.”

The MCP servers are joined by MCP support in Google Cloud’s Apigee platform. The offering provides tools that companies use to build, manage and secure application programming interfaces. Today’s update will make it possible to turn Apigee-powered APIs into MCP servers through a relatively simple workflow.

The new features are rolling out a day after Anthropic PBC, the creator of MCP, donated the technology to a new nonprofit consortium called the Agentic AI Foundation. The group counts Google among its inaugural backers. 

Image: Google