How to Use the Adafruit IO MCP in Vercel AI SDK

Q: How do I stream Adafruit IO data with the Vercel AI SDK?

Use the createMCPClient to connect to your Vinkius endpoint. Then, pass the tools from mcpClient.tools() to the streamText function. The data from tools like listdata will stream directly into your UI components.

Q: Can I build a real-time dashboard for Adafruit IO using the Vercel AI SDK?

Yes. You can use the listfeeds tool to populate a dashboard selector, and then stream data for the selected feed using listdata. The AI SDK's streaming UI capabilities are a great fit for this.

Q: What's the best way to list all my Adafruit IO feeds in a React app with the Vercel AI SDK?

Call the listfeeds tool from your agent. The AI SDK will handle streaming the results, which you can then map into a list in your React component's state. It's the most direct way to get the data into your UI.

Q: Does this MCP server support getting single data points?

It does. The getdata tool is designed for that. You give it the feed and data point ID, and it returns just that single piece of information.

Connect the Vercel AI SDK to your Adafruit IO data through this managed MCP server. Stream sensor readings directly into your React components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adafruit IO MCP to Vercel AI SDK

Create your Vinkius account to connect Adafruit IO 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 Adafruit IO with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live IoT Dashboards with this MCP Server

Pull all your Adafruit IO dashboards and feeds right into your UI. Use `list_dashboards` and `list_feeds` to build out a navigation menu, then call `get_dashboard` to show a specific one. Your users won't wait for a full page load to see their IoT setup. When a user clicks on a feed, you can stream the latest data points directly into a chart. The `list_data` tool gets recent values, and the Vercel AI SDK streams them into your components as they arrive. It feels instant, not like a loading screen.

Get Specific Sensor Readings

Your agent can grab individual data points on command. Just pass a feed key and a data ID to `get_data`. This is perfect for showing the exact value of a sensor at a specific time, like a temperature reading from last Tuesday. Because you're using the AI SDK, this isn't just a backend call. The result streams directly to the frontend, updating a specific part of your UI without a full re-render. You can build interfaces that feel alive with real-time IoT information.

Inspect Triggers and Groups

This server lets you see all your configured triggers and groups. Your agent can use `list_triggers` to get a complete overview or `get_trigger` to inspect a specific one. This is useful for building admin panels where users can see how their automations are set up. Combine this with `list_groups` to get a full picture of your device organization. You can build an interface that shows which devices belong to which group and what triggers are associated with them, all powered by your AI client.

Setup guide

Set up Adafruit IO 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 Adafruit IO 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 Adafruit IO 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 Adafruit IO. 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 Adafruit IO 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 Adafruit IO MCP in Vercel AI SDK

Use the `createMCPClient` to connect to your Vinkius endpoint. Then, pass the tools from `mcpClient.tools()` to the `streamText` function. The data from tools like `list_data` will stream directly into your UI components.

Yes. You can use the `list_feeds` tool to populate a dashboard selector, and then stream data for the selected feed using `list_data`. The AI SDK's streaming UI capabilities are a great fit for this.

Call the `list_feeds` tool from your agent. The AI SDK will handle streaming the results, which you can then map into a list in your React component's state. It's the most direct way to get the data into your UI.

It does. The `get_data` tool is designed for that. You give it the feed and data point ID, and it returns just that single piece of information.

This server only handles your Adafruit IO dashboard, feed, and data point metadata. Your connection is secured by a unique Vinkius endpoint token. The MCP server itself runs in an ephemeral, zero-trust sandbox and does not store your data.

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