Premium Google Home subscribers in the U.S. will be able to let third-party AI agents operate their smart home devices after Google opened early access to a Model Context Protocol server for the Google Home ecosystem. The move lets any agent that supports MCP, including Claude, Hermes, OpenClaw, ChatGPT, and Google Antigravity, interact with devices, view event histories and surface camera summaries using natural language.
Users who want to connect an agent must create a Google Cloud project and configure it to use Home MCP, then hand the MCP configuration to their chosen agent. The agent will prompt the user to sign in and grant permissions before it can access devices or activity logs. A setup guide will be available in the Google Home Developer Center.
The integration covers the full Google Home ecosystem, including Google Nest doorbells and thermostats as well as Works With Google Home and Matter devices such as light bulbs. Google already deploys MCP across other parts of its business, including Google Cloud, data platforms, developer tools and Google Workspace, but this rollout targets consumers experimenting with AI agents for everyday tasks.
Access to the Home MCP will start today and expand over the coming weeks for subscribers to Google Home Premium Advanced in the U.S., the $20-per-month tier that offers longer event-based video history, descriptive notifications, detailed alerts, tools to search video history and daily summaries. Google would not say if or when MCP support would become available to other subscription levels or markets.
During early access Google is seeking feedback from adopters through its Smart Home for Developers Community. For now, the update delivers a path for owners to centralise device control and monitoring through conversational agents, but broader availability and any changes to privacy or billing will depend on the feedback Google receives and future product decisions.
