How to Use the myDevices MCP in AutoGen

Q: How do AutoGen agents divide tasks when monitoring myDevices hardware?

You assign one agent to poll listalerts and another to analyze telemetry using getsensordata. When an alert is detected, they negotiate the correct response payload before a third agent calls the command tool.

Deploy AutoGen multi-agent teams to debate IoT alerts and coordinate physical hardware commands via Cayenne.

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 AutoGen

Create your Vinkius account to connect myDevices to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate AutoGen agent consensus before sending commands

The `send_command` tool is guarded by AutoGen's multi-agent conversation loops to prevent unauthorized or damaging hardware actions. A dedicated AutoGen safety agent reviews the proposed payload against operational limits, while a diagnostic agent uses `get_sensor_data` to verify if the physical state requires intervention. Only when both agents reach a consensus does the system dispatch the command to the Cayenne backend. This multi-perspective check prevents a single faulty sensor reading from triggering catastrophic hardware loops.

Debate IoT alerts using specialized AutoGen roles

Using `list_alerts`, your AutoGen triage agent identifies active system failures and presents them to the specialist group. An AutoGen historical analyst agent calls `get_sensor_history` to check if this alert is a recurring issue or an isolated spike. Meanwhile, an operations agent queries `list_devices` to locate nearby backup systems. The agents debate the severity of the failure in a structured chat, arriving at a validated plan of action before notifying your on-call technician.

Run automated hardware diagnostics via AutoGen

The `list_sensors` tool allows an AutoGen diagnostic team to dynamically inspect every channel on a malfunctioning device using an MCP Server setup. One AutoGen agent queries the sensor list, a second agent pulls active values using `get_device`, and a third agent compares the readings against factory specifications. This collaborative troubleshooting isolates hardware issues down to the specific pin or port. By the time the agents hand off the ticket to a human, they have already ruled out configuration errors and verified physical connectivity.

Setup guide

Set up myDevices MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes myDevices tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="myDevices_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent myDevices data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="myDevices_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent myDevices data")
    print(result.messages[-1].content)

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 AutoGen

You assign one agent to poll `list_alerts` and another to analyze telemetry using `get_sensor_data`. When an alert is detected, they negotiate the correct response payload before a third agent calls the command tool.

Yes, you configure your AssistantAgent constructors to only register `send_command` with your designated execution agent. Diagnostic agents can query `list_devices` but cannot alter physical hardware states.

The agents debate the discrepancy in their chat channel, using `get_sensor_history` to look for patterns of sensor drift. If the data remains inconclusive, they halt automation and log a high-priority alert for human review.

Yes, the server handles asynchronous calls seamlessly, allowing your agents to query multiple sensors or devices in parallel without blocking the main conversation loop.

No, your Cayenne credentials are encrypted and stored securely within the Vinkius platform, injected only at the transport layer. The conversational agents only see the structured outputs of tools like `list_devices` and never touch the raw API keys.

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