Google Home Opens Smart Home Control to Third-Party AI Agents

Google is opening its smart home platform to third-party artificial intelligence agents through a new integration based on the Model Context Protocol, a move that positions the company as infrastructure provider rather than sole interface for connected home devices.

The Google Home MCP integration allows AI tools including Claude, Open Claw, and Google's own Antigravity to access and control devices connected to Google Home, according to Taylor Lehman, group product manager at Google Home & Nest. The integration also grants these agents access to event history and device state data across the entire Google Home ecosystem.

What AI agents can do in your home

The integration enables several capabilities that go beyond simple voice commands. AI agents can perform cross-camera analysis to answer questions like what a child did after arriving home from school, or use device state history to calculate how many loads of laundry were run in a week. Agents can also send audio messages through Google Home speakers and create custom control dashboards.

This layer sits alongside, rather than replacing, Gemini for Home, which remains Google's primary assistant for the Home app and Nest smart speakers following the discontinuation of Google Assistant. The MCP integration provides a separate channel for third-party AI agents to interact with Google Home devices through their own interfaces.

Security constraints and availability

The feature launches with limitations designed to address safety concerns. Google enforces rate limits and safety protections, including blocking agents from unlocking doors. However, Lehman acknowledged that "connecting it to Home MCP can result in unexpected or even undesired behavior," recommending users review Google's developer policies and terms of service.

Access is currently restricted to Google Home Premium Advanced subscribers in the United States, a tier priced at $20 per month or $200 annually. Setup requires creating a Google Cloud project and configuring it for Home MCP use, with rollout beginning in the coming weeks.

Why it matters

This integration represents a strategic shift for Google toward becoming infrastructure for smart home services rather than just a consumer product. By opening its device control and data layer to third-party agents, Google is positioning itself similarly to how AWS provides infrastructure for internet businesses. The approach allows developers to build consumer-facing smart home services on top of Google's platform while keeping users within the Google Home ecosystem. This B2B2C strategy could prove more durable than Google's previous smart home initiatives, though the company's history of abandoned platforms—including Android @ Home, Weave, Project Brillo, and Works with Nest—may make developers cautious about commitment.

The integration also moves smart homes closer to contextual intelligence. Rather than simply executing commands, AI agents with access to home data can troubleshoot devices, suggest automation improvements, and identify patterns across systems—capabilities that traditional smart home platforms typically cannot provide.

Home Assistant, an open-source smart home platform, implemented similar MCP integration that demonstrated the potential for AI agents to handle complex tasks like creating automations and designing dashboards using natural language.

The details were first reported by The Verge.