AI agents are being sold as the solution for planning trips, answering business questions, and solving problems of all kinds, but getting them to work with tools and data outside their chat interfaces has been tricky. Developers have to patch together various connectors and keep them running, but that\u2019s a fragile approach that\u2019s hard to scale and creates governance headaches.<\/p>\n
Google claims it\u2019s trying to solve that by launching its own fully managed, remote MCP servers that would make its Google and Cloud services \u2014 like Maps and BigQuery \u2014 easier for agents to plug into.<\/p>\n
The move follows the launch of Google\u2019s latest Gemini 3 model<\/a>, and the company is looking to pair stronger reasoning with more dependable connections to real-world tools and data.<\/p>\n \u201cWe are making Google agent-ready by design,\u201d Steren Giannini, product management director at Google Cloud, told TechCrunch.\u00a0<\/p>\n Instead of spending a week or two setting up connectors, developers can now essentially paste in a URL to a managed endpoint, Giannini said.<\/p>\n At launch, Google is starting with MCP servers for Maps, BigQuery, Compute Engine, and Kubernetes Engine. In practice, this might look like an analytics assistant querying BigQuery directly, or an ops agent interacting with infrastructure services.\u00a0<\/p>\n In the case of Maps, Giannini said, without the MCP, developers would rely on the model\u2019s built-in knowledge. \u201cBut by giving your agent [\u2026] a tool like the Google Maps MCP server, then it gets grounded on actual, up-to-date location information for places or trips planning,\u201d he added.<\/p>\n Techcrunch event<\/p>\n \n\t\t\t\t\t\t\t\t\tSan Francisco While the MCP servers will eventually be offered across all of Google\u2019s tools, they are initially launching under public preview, meaning they\u2019re not yet fully covered by Google Cloud terms of service. They are, however, being offered at no extra cost to enterprise customers that already pay for Google services.\u00a0<\/p>\n \u201cWe expect to bring them to general availability very soon in the new year,\u201d Giannini said, adding that he expects more MCP servers to trickle in every week.<\/p>\n MCP, which stands for Model Context Protocol, was developed by Anthropic about a year ago as an open source standard to connect AI systems with data and tools. The protocol has been widely adopted across the agent tooling world, and Anthropic earlier this week donated MCP to a new Linux Foundation fund<\/a> dedicated to open sourcing and standardizing AI agent infrastructure.\u00a0<\/p>\n \u201cThe beauty of MCP is that, because it\u2019s a standard, if Google provides a server, it can connect to any client,\u201d Giannini said. \u201cI\u2019m looking forward to seeing how many more clients will emerge.\u201d<\/p>\n One can think of MCP clients as the AI apps on the other end of the wire that talk to MCP servers and call the tools they offer. For Google, that includes Gemini CLI and AI Studio. Giannini said he\u2019s also tried it with Anthropic\u2019s Claude and OpenAI\u2019s ChatGPT as clients, and \u201cthey just work.\u201d<\/p>\n Google argues this isn\u2019t just about connecting agents to its services. The bigger enterprise play is Apigee, its API management product<\/a>, which many companies already use to issue API keys, set quotas, and monitor traffic.\u00a0<\/p>\n
\n\t\t\t\t\t\t\t\t\t\t\t\t\t|
\n\t\t\t\t\t\t\t\t\t\t\t\t\tOctober 13-15, 2026\n\t\t\t\t\t\t\t<\/p>\n