How to Use the myDevices MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK run myDevices commands autonomously?

Yes. The agent evaluates telemetry and calls sendcommand based on your prompt instructions. You configure the guardrails to restrict which commands it can execute.

Connect your OpenAI Agents SDK to the myDevices MCP Server to monitor telemetry and control IoT assets in production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect myDevices MCP to OpenAI Agents SDK

Create your Vinkius account to connect myDevices 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 myDevices with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map IoT assets with OpenAI Agents SDK

Your agent uses `list_applications` and `list_devices` to index your entire myDevices hardware footprint. It pulls the exact hardware IDs and current connection states without you writing manual API wrappers. When a field technician asks for a status report, the SDK triggers `list_sensors`. The agent finds the exact temperature probes or pressure valves attached to that specific unit and formats the output for the dashboard.

Read live telemetry and history

The `get_sensor_data` tool feeds current readings from the MCP Server directly into your agent's context window. If a motor runs hot, the agent knows immediately and logs the incident via your tracing setup. For debugging recurring faults, the agent queries `get_sensor_history`. It pulls time-series data to identify when the temperature spikes started, giving your specialized maintenance agent the context it needs to diagnose the hardware.

Send commands and handle alerts

You can build automated response loops using `send_command`. If an HVAC unit exceeds operating limits, the agent issues a shutdown instruction directly to the device before physical damage occurs. The `list_alerts` tool lets your agent monitor system-wide warnings. You set the guardrails in the SDK, ensuring the agent only acts on critical thresholds and hands off ambiguous warnings to a human operator.

Setup guide

Set up myDevices 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 myDevices tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate myDevices 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="myDevices Agent",
            instructions="You have access to myDevices 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 myDevices. 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 myDevices 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 myDevices MCP in OpenAI Agents SDK

Install the openai-agents package. Create an MCPServerStreamableHttp instance with your myDevices endpoint and pass it to your agent's MCP servers array. Tools load automatically.

Yes. The agent evaluates telemetry and calls send_command based on your prompt instructions. You configure the guardrails to restrict which commands it can execute.

The standard eliminates custom integration code. Your agent discovers the eight myDevices tools immediately, letting you focus on prompt logic instead of maintaining HTTP requests.

Set cacheToolsList=True in your configuration. This prevents the agent from re-fetching the tool schemas on every turn, saving bandwidth for actual get_sensor_data calls.

The server processes hardware telemetry and alert logs. Vinkius runs this MCP connection inside an ephemeral V8 Isolate sandbox, meaning your temperature readings and device IDs disappear the moment the session closes.

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