Google Home MCP now lets AI agents control your smart devices. Google Home MCP is available in early access, giving smart home owners a powerful new way to manage connected devices through AI agents. With this update, Google is bringing the Model Context Protocol to its smart home ecosystem for the first time, opening the door to natural language control and deeper automation.
Google rolled out the Google Home MCP server on Tuesday. This allows any AI agent that supports MCP to securely work with smart home devices and access event history. With Google Home MCP, you can use natural language instructions to review camera summaries, monitor smart home activity, control connected devices, and build custom smart home dashboards. The system is designed to make everyday smart home management simpler and more intuitive.
Which AI Agents Support Google Home MCP?
Any AI agent that supports MCP can connect to the system. Supported agents include:
Claude
Hermes
OpenClaw
ChatGPT
Google Antigravity
These agents can securely interact with your Google Home setup and access your event history. Google Home MCP supports any device in the Google Home ecosystem, including Google Nest doorbells and thermostats, plus “Works with Google Home” (Matter) devices such as light bulbs. This broad compatibility means most existing Google Home users will be able to take advantage of the integration once they have access.
What You Can Do With Google Home MCP
Google Home MCP opens up several practical uses for everyday smart home management:
Review camera summaries using simple natural language commands
Monitor smart home activity without navigating through multiple apps
Control connected devices like lights, thermostats, and doorbells
Build custom smart home dashboards tailored to your specific needs
Instead of tapping through menus and apps, you can delegate tasks to AI agents that understand what you are asking for. This makes routine checks faster and gives you more flexibility in how you interact with your home.
How to Set Up Google Home MCP
Getting started with Google Home MCP requires a few steps. You will need to create a Google Cloud project and configure it to use Home MCP.
After that, you provide the MCP configuration details to your chosen AI agent and ask it to set everything up. The agent will then ask you to sign in and grant permissions. A setup guide is also available in the Google Home Developer Center for additional assistance.
The process is designed for users who are comfortable experimenting with AI agents and cloud tools. Once configured, the connection allows your agent to work directly with your Google Home devices.
Google’s Broader MCP Support
Google already supports MCP in other areas of its business, including Google Cloud, data platforms, developer tools, and Google Workspace. The Google Home MCP rollout targets consumers who are experimenting with AI agents designed to handle everyday tasks. This move shows Google is expanding MCP beyond enterprise and developer use cases into consumer-facing products.
Google Home MCP Availability and Pricing
Access to Google Home MCP begins rolling out today and continues over the coming weeks. It is available to subscribers who pay for Google Home Premium Advanced in the United States.
This is the more expensive subscription tier at $20 per month. It provides features like:
Longer event-based video history
Descriptive notifications and detailed alerts
Tools to search video history
Daily summaries
Google would not comment on if or when Google Home MCP would roll out more broadly, such as to other subscription tiers or markets. For now, access is limited to U.S. users on the premium plan.
Feedback for Early Adopters
Google is soliciting feedback from early adopters during this period through its Smart Home for Developers Community. This suggests the company wants to refine the experience before a wider release. Early users can share their experiences and help shape future updates.
What Google Home MCP Means for Smart Home Users
The Google Home MCP launch signals a shift toward agent-driven smart homes. Rather than manually controlling each device through separate apps, users can rely on AI agents to handle routine tasks and provide quick summaries of home activity.
For now, Google Home MCP remains limited to U.S. subscribers on the premium tier. Whether it expands to more users will depend on how the early access period goes and what feedback Google receives from its developer community. If the rollout goes well, Google Home MCP could become a standard part of the Google Home experience for more users in the future.
