Google Home opens to AI agents via MCP server
Google has launched early access to an MCP server for Google Home, enabling AI agents such as Claude and ChatGPT to control connected devices and review camera summaries. Users need a Google Cloud project and a subscription to the Premium Advanced tier to use the feature. The rollout begins today for U.S. subscribers, with broader availability unclear.
The MCP server connects Google Home's ecosystem to any compatible AI agent, letting users issue natural-language commands for tasks like reviewing camera footage or building custom dashboards. Setup requires a Google Cloud project and configuration steps, though Google provides a developer center guide. The feature supports Nest hardware and third-party Matter devices.
This marks Google's first consumer-facing MCP deployment, following earlier integrations in Cloud, Workspace, and developer tools. Access is initially limited to U.S. subscribers of the $20-per-month Premium Advanced tier, with rollout continuing over coming weeks. Google is gathering early-adopter feedback through its developer community but hasn't specified broader availability.
This move could shift how households interact with smart home technology, moving from app-based controls to conversational AI management. Users who pay for Premium Advanced may gain convenience, but the requirement for a Google Cloud project adds technical friction that could limit adoption to enthusiasts. Privacy implications may emerge as AI agents gain access to camera summaries and event histories, potentially raising concerns about data handling and third-party agent access.