How to Use the myDevices MCP in Vercel AI SDK

Q: How do I get sensor data from myDevices using the Vercel AI SDK?

You call the getsensordata tool. Pass it to the generateText or streamText function from the Vercel AI SDK, and the result will stream directly into your UI components.

Q: Can I list all my devices from myDevices in a Next.js app with the Vercel AI SDK?

Yes. The listdevices tool gives you the full inventory. Your AI agent can call it and you can easily map the results to a list in your React components.

Q: Is it possible to send commands to myDevices hardware with the Vercel AI SDK?

Absolutely. The sendcommand tool is what you'll use. You can hook it up to a button in your app to trigger actions on your IoT hardware.

Q: How does this MCP Server help with debugging myDevices issues in the Vercel AI SDK?

It gives you direct access to logs and history. Use listalerts to see what's currently broken, and then pull getsensorhistory to see the events leading up to the failure.

Connect your Vercel AI SDK app to the myDevices MCP Server. Stream IoT data directly into your UI and watch sensor values update live.

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 Vercel AI SDK

Create your Vinkius account to connect myDevices to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live IoT Dashboards

Connect your UI to real-world hardware. Use `get_sensor_data` to stream telemetry from any device directly into your React or Svelte components. The Vercel AI SDK renders data as it arrives, so your users see temperatures and statuses change in real time. It's not just for reading data. You can build interactive controls, too. Let users trigger actions on physical devices by calling `send_command` from your frontend. Your AI client handles the call to the myDevices MCP server, and you just manage the UI state.

Manage Your Device Fleet

Get a complete picture of your hardware. The `list_devices` and `list_sensors` tools let you build UIs that catalog every asset connected to your myDevices account. Your agent can fetch this info and stream it right into a table or list view. Need to dig into a specific device? Just call `get_device` to pull up its detailed properties. This is perfect for creating detail pages or modals that show a device's full configuration without a page reload.

Monitor Alerts with your Vercel AI SDK

This MCP Server lets you build an active alert console. The `list_alerts` tool pulls all current alerts from your myDevices account. Your agent can call this on a timer or on-demand to keep your UI's alert feed current. Combine this with historical context. When an alert fires, you can use `get_sensor_history` to pull the last few hours of data for that sensor. This gives your users the context they need to understand what went wrong, right in the same interface.

Setup guide

Set up myDevices MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all myDevices tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent myDevices transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You call the `get_sensor_data` tool. Pass it to the `generateText` or `streamText` function from the Vercel AI SDK, and the result will stream directly into your UI components.

Yes. The `list_devices` tool gives you the full inventory. Your AI agent can call it and you can easily map the results to a list in your React components.

Absolutely. The `send_command` tool is what you'll use. You can hook it up to a button in your app to trigger actions on your IoT hardware.

It gives you direct access to logs and history. Use `list_alerts` to see what's currently broken, and then pull `get_sensor_history` to see the events leading up to the failure.

All requests for sensor telemetry and device commands are proxied through Vinkius's ephemeral sandboxes. Your Vercel AI SDK client only needs a single Vinkius token, so your myDevices credentials are never exposed to the frontend.

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