How to Use the Google Home MCP in OpenAI Agents SDK

Q: How do I configure Google Home tools inside OpenAI Agents SDK?

Install the package with pip install openai-agents and initialize the server using MCPServerStreamableHttp. You then pass this instance inside the mcpservers list when instantiating your Agent. The agent automatically discovers the 12 Nest tools.

Q: How does OpenAI Agents SDK handle expired Nest camera streams?

The SDK relies on your agent calling generatecamerastream to fetch a fresh token right before rendering. If a stream hangs, the agent uses stopcamerastream to clean up the stale connection.

Q: What is the best way to avoid hitting Nest API rate limits?

Set cacheToolsList=True in your server parameters to stop the agent from constantly querying the MCP server schema. For device states, have the agent call getdevice only when a state change is actually requested instead of polling.

Control your Nest devices with OpenAI Agents SDK using safe, auto-discovered MCP tools and built-in runtime guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Google Home to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage climate controls safely with OpenAI Agents SDK

`set_thermostat_mode` lets your agent switch Nest operating modes between heat, cool, off, or eco ranges. You pass the server to your agent constructor, and OpenAI automatically discovers the schema. Built-in guardrails validate these temperature changes before they execute on your physical hardware, blocking dangerous thermal spikes. When your target temperature needs a direct adjustment, `set_thermostat_heat` and `set_thermostat_cool` handle the precise thermal changes. Tracing on the OpenAI dashboard lets you monitor every command. You see exactly when and why an agent triggered a climate change, keeping your automated home predictable.

Map your home layout using this MCP Server

`list_structures` is the starting point for mapping every physical property connected to your Google Nest account. The tool returns the basic structural framework of your smart home. From there, your agent calls `list_rooms` to understand exactly which devices live in which physical spaces. Your agent uses `list_devices` to discover every thermostat, camera, and fan across those rooms. This systematic discovery ensures the agent never attempts to send commands to a device that does not exist. It builds a clean, cached map of your physical hardware in memory.

Monitor live video feeds on demand

`generate_camera_stream` creates a temporary feed URL directly from your Nest cameras or doorbells. Your agent spins up these live streams when motion is detected or when a user explicitly asks for a visual check. Because these stream tokens expire quickly, the agent must serve them to the user immediately. `stop_camera_stream` terminates the active video session as soon as the viewing window closes. This action prevents your system from wasting precious bandwidth and Google SDM API quota. Your agent handles this cleanup automatically, keeping your connection pool clear.

Setup guide

Set up Google Home MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Google Home tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Google Home tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Google Home tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Google Home Agent",
            instructions="You have access to Google Home tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package with `pip install openai-agents` and initialize the server using `MCPServerStreamableHttp`. You then pass this instance inside the `mcp_servers` list when instantiating your Agent. The agent automatically discovers the 12 Nest tools.

Yes, you can restrict access by filtering the tool list before passing it to the agent constructor. This prevents the agent from calling high-impact tools like `set_thermostat_mode` while still allowing read-only queries like `list_devices`.

The SDK relies on your agent calling `generate_camera_stream` to fetch a fresh token right before rendering. If a stream hangs, the agent uses `stop_camera_stream` to clean up the stale connection.

Set `cacheToolsList=True` in your server parameters to stop the agent from constantly querying the MCP server schema. For device states, have the agent call `get_device` only when a state change is actually requested instead of polling.

All video tokens and structure layouts are processed inside an ephemeral V8 Isolate sandbox. No credentials or live stream URLs are saved to disk or stored on Vinkius servers. Your Google SDM authentication tokens remain fully encrypted in transit and are immediately purged after each API call.

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