How to Use the Home Assistant MCP in Vercel AI SDK

Q: How do I connect Home Assistant to Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient with your HTTP endpoint URL. Pass the resulting tools directly into your function to let your AI client manage your home using this MCP setup.

Q: How does the agent discover available services?

The agent runs listavailableservices to get a list of active domains and actions. This prevents the model from hallucinating service calls that don't exist on your specific setup.

Stream real-time smart home states directly into React components 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 Home Assistant MCP to Vercel AI SDK

Create your Vinkius account to connect Home Assistant 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 Home Assistant with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live state streaming with Vercel AI SDK

This MCP Server exposes `list_entity_states` to fetch the current status of every smart device in your setup. Your React or Next.js frontend gets these raw entity IDs, state values, and last-changed timestamps immediately. The AI client processes this data to render live toggles or sliders on the page.

Direct device control from the UI

The `call_ha_service` tool executes physical changes across your home's domains like lights, climate control, and smart switches. By combining this MCP connection with the Vercel AI SDK, your interface updates dynamically as the service call completes. Under the hood, the agent handles the JSON parameters so your users just speak or type naturally to adjust their physical environment.

Dynamic template rendering and validation

The `render_ha_template` tool evaluates complex Jinja2 templates directly on your local Home Assistant instance. Before running any heavy automations, the agent uses `check_ha_configuration` to ensure your local setup is completely valid. Running this check prevents broken configurations from stalling your live production edge functions.

Setup guide

Set up Home Assistant 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 Home Assistant 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 Home Assistant 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 Home Assistant. 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 Home Assistant 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 Home Assistant MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` with your HTTP endpoint URL. Pass the resulting tools directly into your function to let your AI client manage your home using this MCP setup.

Yes. You control this by limiting the entities exposed to the long-lived access token on your local instance. The `list_entity_states` tool will only return the devices you explicitly allow.

No, your Edge Functions need an active network path to reach your local instance. The `get_api_status` tool verifies this connection is active before your agent attempts to run any automation tasks.

The agent runs `list_available_services` to get a list of active domains and actions. This prevents the model from hallucinating service calls that don't exist on your specific setup.

All entity states, calendar events, and device configurations stay inside your local network or transit securely via HTTPS. The Vinkius sandbox isolates the connection, meaning no raw home data is stored or exposed to external third parties.

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