How to Use the myDevices MCP in Pydantic AI

Q: How do I initialize the myDevices MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp. Use the MCPToolset class with your HTTP endpoint and pass it to your Agent's toolsets parameter. Remember that MCPServerHTTP is deprecated.

Q: Will Pydantic AI catch bad myDevices sensor data?

Yes. If getsensordata returns a null value or unexpected format, the framework fails loudly. You catch the error in code rather than acting on corrupt telemetry.

Q: How do I list hardware components safely?

Your agent calls listdevices to get the parent units, then iterates with listsensors. The framework validates the schema of every single component returned by the API.

Build type-safe myDevices agents with Pydantic AI and this MCP Server to validate every sensor reading and hardware command.

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 Pydantic AI

Create your Vinkius account to connect myDevices 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 myDevices with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly type myDevices with Pydantic AI

The `get_sensor_data` tool returns exact telemetry values that your agent validates against rigid models. If a temperature sensor returns a string instead of a float, the framework throws a validation error immediately. This strictness applies to `list_alerts` as well. Your agent parses incoming warnings into predictable structures, guaranteeing no hallucinated severity levels or missing timestamps enter your application logic.

Map hardware without silent failures

Calling `list_devices` through the MCP Server builds a verified inventory of your physical assets. The agent checks every device ID and connection status against your expected schema before proceeding. When checking specific components via `list_sensors`, the agent confirms the exact sensor type. You never accidentally send a reboot command to a passive temperature probe because the types simply will not allow it.

Safely execute remote commands

The `send_command` tool pushes instructions to your edge devices. Because Pydantic AI validates the payload before execution, you eliminate the risk of sending malformed JSON or invalid parameters to your hardware. If an intervention fails, the agent pulls `get_sensor_history` to verify the state change. It ensures the command actually affected the physical environment, giving you absolute confidence in your automated systems.

Setup guide

Set up myDevices 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": {
        "mydevices-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent myDevices 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 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 Pydantic AI

Install pydantic-ai-slim[mcp]. Use the MCPToolset class with your HTTP endpoint and pass it to your Agent's toolsets parameter. Remember that MCPServerHTTP is deprecated.

Yes. If get_sensor_data returns a null value or unexpected format, the framework fails loudly. You catch the error in code rather than acting on corrupt telemetry.

Yes. Pydantic AI is model-agnostic. You can route your myDevices data through OpenAI, Anthropic, or a local model running on your own hardware.

Your agent calls list_devices to get the parent units, then iterates with list_sensors. The framework validates the schema of every single component returned by the API.

This connection touches alert logs and live telemetry. Vinkius hosts the endpoint in an isolated container that spins up for the request and instantly dies, leaving zero trace of your hardware states.

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