How to Use the Home Assistant MCP in Google ADK

Q: How can I use Google ADK to analyze Home Assistant energy usage?

Your Gemini agent can use the getentityhistory tool to pull historical data from your energy sensor. Then, because it's running in the Google ecosystem, it can directly push that data into a BigQuery table for analysis.

Q: Is it possible to list all Home Assistant services with a Google ADK agent?

Yes. The agent should call the listavailableservices tool. This returns a complete list of all domains and the services they support, which is essential for discovering what your specific Home Assistant configuration can do.

Connect Google Cloud agents to your Home Assistant instance for massive-scale automation and data analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Home Assistant MCP to Google ADK

Create your Vinkius account to connect Home Assistant 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 Home Assistant with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe Home Data Directly to BigQuery

Your agent can pull months of data from a single sensor using `get_entity_history`. With a Gemini model's long-context window, it can analyze the entire dataset in one shot to identify trends, without batching or chunking. From there, the agent can push that structured data straight into a BigQuery table. This lets you correlate your home's energy consumption from `sensor.power_meter` with public weather datasets or occupancy patterns, all from a single agent running on Google Cloud.

Run Complex Logic with this MCP Server

A Google ADK agent can build a complete operational model of your home. It starts with `list_entity_states` and `list_available_services` to map out every device and its capabilities. This isn't just about turning a light on; it's about asking the agent to run a full diagnostic on all `climate` entities and report anomalies. The `render_ha_template` tool is key for offloading work. Your agent can use it to run complex Jinja2 logic on your Home Assistant instance, like checking multiple sensor values before deciding to `call_ha_service`. It keeps your agent focused on high-level goals.

Trigger Automations from Vertex AI

Connect your cloud infrastructure to your physical world. A Vertex AI pipeline can invoke your agent to act on a prediction. For example, a model forecasts high energy prices, triggering the agent to `call_ha_service` and set all thermostats to an economy mode. Before it acts, the agent confirms the connection is live with `get_api_status` and that the system is healthy with `check_ha_configuration`. This MCP server provides a reliable, managed bridge between your Google Cloud AI and your smart home hardware.

Setup guide

Set up Home Assistant 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 Home Assistant 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="Home Assistant_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Home Assistant 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 Home Assistant. 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 Home Assistant 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 Home Assistant MCP in Google ADK

Your Gemini agent can use the `get_entity_history` tool to pull historical data from your energy sensor. Then, because it's running in the Google ecosystem, it can directly push that data into a BigQuery table for analysis.

Absolutely. Once connected to this MCP server, your Google ADK agent can use the `call_ha_service` tool to control any device, from lights and switches to thermostats and media players in your Home Assistant setup.

Yes. The agent should call the `list_available_services` tool. This returns a complete list of all domains and the services they support, which is essential for discovering what your specific Home Assistant configuration can do.

The MCP server is hosted by Vinkius, so latency depends on the round trip from your Google Cloud region to Vinkius and then to your local Home Assistant instance. For control actions, expect responses in the sub-second range, assuming your local network is stable.

The server only touches data your agent explicitly requests, like entity history or calendar events. Vinkius isolates each MCP server connection, manages the API token securely, and ensures all requests are stateless and ephemeral. Nothing is stored long-term.

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