How to Use the Google Home MCP in Pydantic AI

Q: How do I connect Google Home tools to Pydantic AI?

Run pip install "pydantic-ai-slimmcp" and initialize the connection using MCPToolset("http://..."). Pass this toolset directly into the toolsets argument of your Pydantic AI Agent.

Q: Is the old MCPServerHTTP class still supported?

No, MCPServerHTTP is deprecated in recent versions of the framework. You should use the unified MCPToolset class to handle your server connections.

Build type-safe Nest automations with Pydantic AI and this MCP Server to catch API errors before they hit physical devices.

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 Pydantic AI

Create your Vinkius account to connect Google Home to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate your Nest climate states with Pydantic AI

`set_thermostat_heat` changes the target temperature on your physical Nest unit after validating the payload against strict Python types. Pydantic AI ensures that any input temperature is a valid float within Google's allowed range before calling the API. If your agent tries to set a room to a thousand degrees, the framework blocks it instantly. For cooling adjustments, `set_thermostat_cool` and `set_thermostat_range` provide the same type-safe guarantees. This runtime validation prevents malformed commands from causing silent failures. Your code either runs with perfect data or fails loudly so you can fix it.

Map structures safely using this MCP Server

`list_structures` queries your Google Nest account to return a structured list of your physical homes. The server parses the raw JSON response and validates it against strict schemas before your agent ever sees it. This prevents unexpected API changes from breaking your automation pipelines. Your agent then calls `list_rooms` and `list_devices` to map out the rest of your smart home layout. Because every field is typed, your code can confidently navigate rooms and device IDs. You write clean Python code without worrying about missing dictionary keys.

Manage camera streams and eco modes safely

`generate_camera_stream` returns a verified URL and access token for your Nest camera feeds. Pydantic AI validates the stream response structure, ensuring your agent gets a clean, uncorrupted URL string. When the viewing session ends, the agent calls `stop_camera_stream` to close the connection cleanly. `set_thermostat_eco` lets you trigger energy-saving mode with a single validated call. If you need to run the fan instead, `set_fan_timer` accepts a strictly typed duration integer. This level of type safety makes your home automation reliable enough for production deployments.

Setup guide

Set up Google Home MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "google-home-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Google Home tools.",
)

result = await agent.run("List recent Google Home transactions")
print(result.output)

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 Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"` and initialize the connection using `MCPToolset("http://...")`. Pass this toolset directly into the `toolsets` argument of your Pydantic AI Agent.

The framework will raise a validation error immediately. Instead of passing corrupt or hallucinated data to your agent, the system fails loudly, allowing you to catch API mismatches in your logs.

Yes, this MCP Server supports both Streamable HTTP and SSE transports. You configure the `MCPToolset` with your Vinkius HTTP endpoint, and the framework manages the underlying connection pool.

No, `MCPServerHTTP` is deprecated in recent versions of the framework. You should use the unified `MCPToolset` class to handle your server connections.

We use a zero-trust V8 Isolate architecture to process your SDM API calls. Your physical structure layouts and camera stream tokens are never written to persistent storage. All authentication details are handled purely in memory and discarded the moment your request completes.

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