What Google Nest devices are supported by this API?

The SDM API supports: Nest Thermostats (Nest Learning Thermostat, Nest Thermostat E, Nest Thermostat 2020), Nest Cameras (legacy, battery, wired, with spotlight), Nest Doorbells (legacy battery, wired, battery), and Nest Hub displays. Each device exposes specific traits (e.g., ThermostatMode, CameraLiveStream) that can be queried and controlled.

How do I get OAuth 2.0 credentials for the Google SDM API?

Visit the [**Google Device Access console**](https://console.nest.google.com/device-access/) and create a project. You'll receive a Project ID. Then, set up OAuth 2.0 credentials in Google Cloud Console, link them to your Device Access project, and complete the OAuth flow to obtain an access token. The token expires after 1 hour and must be refreshed.

Can I control multiple thermostats in different locations?

Yes! The API returns all devices across all structures and rooms in your project. Use `list_devices` to see all thermostats with their room assignments, then use each device's unique ID to control them individually. You can set different modes and temperatures for each thermostat.

How long do camera stream URLs last?

Camera stream URLs (both RTSP and WebRTC) are temporary and typically expire after 5 minutes. The stream token returned in the response should be used immediately and the stream should be stopped with `stop_camera_stream` when no longer needed to free up device resources.

Google Home MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Google Home
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Google Home through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Google Home "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Google Home?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Google Home MCP Server

Connect to Google Nest devices via the Smart Device Management (SDM) API and control your smart home from any AI agent. Manage thermostats, view camera feeds, and interact with doorbells.

Pydantic AI validates every Google Home tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

List Devices — See all your Nest thermostats, cameras, doorbells, and displays
Thermostat Control — Set mode (Heat/Cool/Off), adjust temperatures, enable eco mode, and control fan timer
Camera Streaming — Generate live RTSP or WebRTC stream URLs from Nest cameras and doorbells
Doorbell Management — View doorbell camera feeds and stream events
Structure & Rooms — Browse your home's structures and room organization
Device Details — Get full device state including all traits and current settings

The Google Home MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Google Home to Pydantic AI via MCP

Follow these steps to integrate the Google Home MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Google Home with type-safe schemas

Why Use Pydantic AI with the Google Home MCP Server

Pydantic AI provides unique advantages when paired with Google Home through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Google Home integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Google Home connection logic from agent behavior for testable, maintainable code

Google Home + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Google Home MCP Server delivers measurable value.

Type-safe data pipelines: query Google Home with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Google Home tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Google Home and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Google Home responses and write comprehensive agent tests

Google Home MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Google Home to Pydantic AI via MCP:

generate_camera_stream

The stream token is temporary and should be used immediately. Stop the stream when done. Generate a live camera stream URL from a Nest camera or doorbell

get_device

Use device ID from list_devices or device name. Get details for a specific Google Nest device

list_devices

Shows device types, traits, and room assignments. USE WHEN: - User wants to see all their Nest devices - User needs to find device IDs for other commands - User is exploring their smart home setup - User asks "what Nest devices do I have" EXAMPLES: - "List all my Nest devices" → call with no params - "Show my smart home devices" → call with no params - "What Nest devices are connected?" → call with no params List all Google Nest devices in your home

list_rooms

Useful for understanding device locations and room organization. List all rooms in a specific structure

list_structures

Each structure contains rooms and devices. List all structures (homes) in your Google Nest account

set_fan_timer

Turns the fan on for a specified duration. Duration is optional and defaults to the thermostat setting. Set the fan timer on a Nest thermostat

set_thermostat_cool

Use this when the thermostat is in COOL or HEATCOOL mode. Set the cooling temperature on a Nest thermostat

set_thermostat_eco

This is a manual override of the eco/eco-friendly temperature settings. Set Nest thermostat to eco mode for energy savings

set_thermostat_heat

Use this when the thermostat is in HEAT or HEATCOOL mode. Set the heating temperature on a Nest thermostat

set_thermostat_mode

Supported modes: HEAT, COOL, HEATCOOL, OFF. Use device ID from list_devices to target a specific thermostat. USE WHEN: - User wants to change thermostat mode - User asks to turn heating/cooling on or off - User wants to switch thermostat operating mode - User says "set thermostat to heat/cool/off" PARAMETERS: - device_id (REQUIRED): Thermostat device ID - mode (REQUIRED): One of HEAT, COOL, HEATCOOL, or OFF EXAMPLES: - "Set thermostat to heat mode" → call with device_id, mode="HEAT" - "Turn off the thermostat" → call with device_id, mode="OFF" - "Set thermostat to cool" → call with device_id, mode="COOL" Set the mode of a Nest thermostat

set_thermostat_range

Useful for HEATCOOL mode to define the comfort range. Set both heating and cooling temperatures on a Nest thermostat

stop_camera_stream

Use the stream token returned from generate_camera_stream to properly terminate the stream session. Stop an active camera stream from a Nest camera or doorbell

Example Prompts for Google Home in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Google Home immediately.

"List all my Nest devices and show me what thermostats I have."

"Set my living room thermostat to 22°C heating mode."

"Show me the live feed from my front door camera."

Troubleshooting Google Home MCP Server with Pydantic AI

Common issues when connecting Google Home to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Google Home + Pydantic AI FAQ

Common questions about integrating Google Home MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Google Home MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.