On September 16, 2026, Google did something it has never done before: it opened Google Home to other companies' AI agents. The company announced early access to Home MCP, a server that turns your smart home into something any MCP-compatible agent can connect to, query, and control. "With Google Home MCP, any agent that supports calling MCP tools, such as Google Antigravity, Claude, Hermes, OpenClaw or others, can now interact with all of the devices and event history in the Google Home ecosystem, from your Google Nest doorbell and thermostat to your Works with Google Home (or Matter) light bulbs," wrote Taylor Lehman, Group Product Manager for Google Home & Nest.
It is a small feature announcement with a large meaning: the biggest smart home platform just adopted a protocol invented by Anthropic to let competitor AI agents touch its own hardware.
In short:
- Google Home is now an MCP server: agents can list homes, read device states, run actions, and read event history.
- Early access was announced September 16, 2026, and Google said it would roll out gradually to US English subscribers of Google Home Premium Advanced.
- Documented setup guides exist for Antigravity, Claude (Cowork), and OpenClaw. Hermes is named in Google's post as an example agent alongside Antigravity, Claude and OpenClaw.
- Sensitive actions are walled off: unlocking doors is the only block Google has confirmed in writing. Garage and alarm limits are reported by media, not documented by Google.
- The setup requires a Google Cloud project and OAuth consent.
What Just Launched
Home MCP is a Model Context Protocol server that exposes your Google Home setup to external AI agents. If that sentence means nothing to you, think of it as a set of well-defined doors: an agent can knock on each one, ask a structured question, and get a structured answer. Google's announcement post frames it as "enabling your agent to interact with your home."
The rollout is deliberately gradual. Early access started September 16, 2026, in US English, and Google said the feature would reach Google Home Premium Advanced subscribers gradually. If you pay for it, check whether it has reached your account.
The headline price detail: MCP access requires a Google Home Premium Advanced subscription. Reports at launch put it at $20 a month or $200 a year, and Google's developer documentation does not list a price, so confirm it on Google's Premium page.
What Your Agent Can Actually Do
Google's Home MCP developer reference documents five tools an agent can call:
- list_homes gives the agent the list of homes it is allowed to see.
- list_home_resources lists the devices, rooms and device capabilities in each home.
- list_home_states reads the current state of those devices (lights on or off, thermostat setpoints, lock status).
- run_home_actions executes changes: turn devices on and adjust their settings.
- list_home_history reads event history, including camera and doorbell activity.
That last one is the one that matters most. Camera and doorbell history in an agent's context window is genuinely useful - "did anyone approach the front door while I was out?" becomes a question any connected agent can answer. It is also the one with the most obvious privacy weight, which Google addresses with the permission boundary described below.
What Your Agent Can't Do (and What Nobody's Sure About)
The catch is that "control" stops short of the dangerous stuff. Google's developer documentation says the server prohibits "sensitive actions like unlocking doors." An agent can read that a lock is locked; it cannot flip it to unlocked.
Beyond that, the picture gets murkier. Media coverage, including The Verge, reports that garage doors and alarm disarming are also off the table for agents. Google has not published an exhaustive list of blocked actions, so treat those two as expected limits rather than documented policy.
This distinction matters for how you trust the system. A hard, documented block on unlocking doors is a real safety rail. A reported-but-undocumented limit is a reasonable expectation, but it could change - in either direction - as Google iterates on early access.
How to Connect an Agent to Google Home
The setup is more than a toggle. Based on Google's developer docs, the flow is:
- Confirm your subscription. You need an active Google Home Premium Advanced subscription on the account that owns the home.
- Create a Google Cloud project. Home MCP runs through a project you set up in Google Cloud, with OAuth consent configured for the
home.platform.v2scope. - Configure your agent. Each documented client has a setup guide: Google's announcement post links configuration walkthroughs for Antigravity, Claude (Cowork), and OpenClaw.
- Test with safe actions first. Turn a light on and off before you ask the agent anything about locks or cameras.
If the OAuth consent screen fails, check that your agent's redirect URI exactly matches the one in the Cloud project. We did not test this setup, so treat that as a general OAuth check, not a documented Home MCP fix.
Should You Actually Connect One?
The honest answer: it depends on how much you trust the agent and how much you value the convenience.
The capability map above is real utility - event history alone makes this more than a gimmick. But you are handing an LLM a live view of your home state and, if you connect cameras, a record of who came to your door. The sensible posture is to connect one agent you actually use, give it the least-privileged home (or a test home with dummy devices), and keep the blocked-actions list in mind.
There is also the protocol question. MCP is Anthropic's protocol, released November 2024, and it has become a common way for AI tools to expose capabilities to agents. Google adopting it for its own hardware, so that an agent like Claude can read your Nest doorbell history, is a strong sign of that. For a look at how teams put MCP to work with guardrails, see governed multi-agent workflows with n8n and Claude, or how Kick AI exposes bookkeeping to agents over MCP.
And if you are watching from outside the US, or on the cheaper Premium Standard tier: no timeline yet. Google's announcement is US English only, with no published schedule for other regions or tiers.
The Bottom Line
Google Home MCP is a genuinely big deal wrapped in a small subscription-gated feature. The capability is real, the safety boundary is (mostly) clear, and the setup is a manageable project for anyone already paying for the Advanced tier. For everyone else, it is a preview of how every platform will eventually talk to agents.
Plan details are as reported at launch in September 2026 and can change. Confirm on Google's Premium page.
