
Google announced this week that it’s leveraging the Model Context Protocol (MCP), an open-source framework for connecting AI chatbots to external systems, to open up its Google Home ecosystem to third-party AI agents. This will allow users of Anthropic’s Claude, OpenClaw, and other AI tools that support the Model Context Protocol to control smart home devices that integrate with Google Home.
The Home MCP integration is currently available in early access for Google Home Premium Advanced users in the US. Advanced users can test it to analyze data from Google Nest doorbells, light bulbs that integrate with Google Home or support the Matter standard, and more.
“This gives your favorite AI agent real-world physical context—allowing it to analyze and answer questions about home activity, summarize camera footage across rooms, manage devices on your behalf, or even create your own smart home dashboards using everyday language,” the company explained yesterday.
Google did warn that beta testers should take into consideration the risks of granting third-party AI agents access to their smart home devices. However, the company implemented rate limits and safety protections, and third-party agents won’t be able to perform sensitive actions such as unlocking doors. You can visit the Google Home Developer Center to learn more about how to get started with Home MCP.