How to Use the Balena MCP in Vercel AI SDK

Q: How do I connect the Balena MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and initialize with createMCPClient. Point the HTTP transport URL to your Vinkius endpoint. Pass mcpClient.tools() into streamText to let the agent start querying your devices.

Q: Do I need to close the MCP Server connection?

Always call mcpClient.close() when your Edge Function finishes the stream. Leaving it open causes memory leaks in serverless environments.

Build React dashboards that stream live IoT fleet data from the Balena MCP Server directly to your users with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Balena MCP to Vercel AI SDK

Create your Vinkius account to connect Balena 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 Balena with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live fleet metrics into Next.js UIs

Your Vercel AI SDK application queries edge nodes using the `list_devices` tool. We pass OData filters like `$filter=uuid eq '<UUID>'` directly to the MCP Server, keeping the payload small. That means your frontend only receives the exact device statuses it needs right now. Because this transport uses HTTP streaming, the result pipes straight into your React components. Users watch their dashboard populate with offline indicators and battery levels instantly instead of staring at a spinning wheel.

Push edge config changes through chat

Giving users control over remote hardware requires the `create_device_env_var` tool. They type a command into your interface, and the agent triggers an environment update on the target Raspberry Pi. The Vercel AI SDK handles the tool call while keeping the UI responsive. You also get `create_device_tag` for organizing those endpoints. Tagging physical hardware from a web app usually means writing custom backend routes, but here the agent does the heavy lifting while streaming the confirmation text back to the browser.

Expose Balena firmware data securely

Fetching the exact firmware running on edge hardware requires the `list_releases` tool. The agent pulls the application fleet ID and fetches the current release history. It formats the version numbers into your Svelte or Vue tables without manual data mapping. Grabbing upgrade images works the same way with `get_os_download_url` and `list_os_versions`. Your client fetches the exact balenaOS image link for their specific board architecture and presents a one-click download button right in the chat window.

Setup guide

Set up Balena 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 Balena 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 Balena 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 Balena. 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 Balena 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 Balena MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize with `createMCPClient`. Point the HTTP transport URL to your Vinkius endpoint. Pass `mcpClient.tools()` into `streamText` to let the agent start querying your devices.

Yes. The agent uses OData parameters inside the tool calls. It passes `$filter=slug eq ''` to `list_fleets` so you only pull data for the specific application you care about.

Always call `mcpClient.close()` when your Edge Function finishes the stream. Leaving it open causes memory leaks in serverless environments.

Tool results stream immediately once the Vinkius sandbox responds. You render the text chunks as they arrive rather than waiting for the entire IoT registry to download.

This integration reads fleet structures, device UUIDs, OS versions, and API keys. Vinkius runs the query in an ephemeral V8 isolate that destroys itself after execution. Your IoT credentials never persist on our infrastructure.

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