How to Use the Google Home MCP in Google ADK

Q: How do I initialize the Google Home toolset in Google ADK?

Install the framework using pip install google-adk and define your tools using McpToolset. Pass this toolset directly to your LlmAgent instance to expose all 12 Nest capabilities to Gemini.

Q: How does Google ADK handle long-context reasoning with Google Home devices?

Gemini models ingest your entire device list from listdevices into their massive context window. This allows the agent to make complex, multi-step decisions about climate and cameras without losing track of previous commands.

Q: Can I restrict which Nest devices the agent can control?

Yes, you can pass an optional toolnames filter to your McpToolset constructor. This lets you exclude specific tools like setthermostatmode if you want a read-only monitoring agent.

Control your Nest devices with Google ADK to run smart home automation directly from your enterprise Gemini models using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Home MCP to Google ADK

Create your Vinkius account to connect Google Home to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google Home with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect your Nest hardware to Google ADK

`list_devices` acts as the primary discovery tool for your Gemini-powered enterprise agents. It outputs a clean list of device types, traits, and current room assignments directly into your agent's long-context window. Since Gemini handles over a million tokens, it easily parses your entire home layout in one go. Once your agent knows what hardware is online, `get_device` pulls the exact state of any specific Nest unit. This tool feeds real-time status data directly into your Google Cloud pipelines. You can easily combine this device data with corporate datasets stored in BigQuery.

Run smart climate rules with this Google Home MCP Server

`set_thermostat_mode` switches your Nest thermostat between heat, cool, eco, or off modes. Your enterprise agent invokes this tool based on external data sources like regional weather forecasts or energy grid pricing. It translates high-level logic into direct physical actions. For fine-grained control, `set_thermostat_range` defines the exact heating and cooling limits for dual-action comfort. The agent can also trigger `set_fan_timer` to circulate air when rooms get stuffy. This setup keeps your buildings comfortable without wasting energy.

Control security feeds and eco settings

`generate_camera_stream` fetches a live video feed URL from any Nest camera or doorbell on your property. This tool allows your Gemini agent to inspect visual security events directly within its reasoning loop. The temporary stream token ensures your security feeds are never exposed longer than necessary. `set_thermostat_eco` overrides your current schedule to force energy-saving mode instantly. This is perfect for automated weekend shutdowns or unexpected vacant periods. When the building is occupied again, the agent restores normal operations using standard temperature tools.

Setup guide

Set up Google Home MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Google Home tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Google Home_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Google Home tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google Home / Nest. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google Home now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google Home MCP in Google ADK

Install the framework using `pip install google-adk` and define your tools using `McpToolset`. Pass this toolset directly to your `LlmAgent` instance to expose all 12 Nest capabilities to Gemini.

Yes, this MCP Server supports both Stdio and Streamable HTTP transports. You simply pass the HTTP endpoint URL into your `StreamableHttpServerParameters` when setting up the ADK toolset.

Gemini models ingest your entire device list from `list_devices` into their massive context window. This allows the agent to make complex, multi-step decisions about climate and cameras without losing track of previous commands.

Yes, you can pass an optional `tool_names` filter to your `McpToolset` constructor. This lets you exclude specific tools like `set_thermostat_mode` if you want a read-only monitoring agent.

Your temperature settings and structure layouts are processed in a zero-trust, isolated environment. Vinkius uses ephemeral V8 sandboxes that handle your SDM credentials in memory only. No device configurations or temperature logs are ever persisted or exposed to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript