How to Use the Hologram.io MCP in Vercel AI SDK

Q: How do I connect Hologram.io to my Vercel AI SDK project?

You'll use the createMCPClient function from the AI SDK. Point it to the Vinkius endpoint URL for this server, and then pass the mcpClient.tools() output to your generateText or streamText call. Don't forget to call mcpClient.close() when you're done.

Q: Can I stream device locations from Hologram.io with the Vercel AI SDK?

Yes. When your agent calls getdevicelocations, the Vercel AI SDK will stream the results directly into your frontend components. This is ideal for building live maps or location-aware UIs without waiting for the full list to load.

Build live IoT dashboards in your Next.js app with Hologram.io and the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hologram.io MCP to Vercel AI SDK

Create your Vinkius account to connect Hologram.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 Hologram.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Fleet Map

Stream device status directly into your UI. Your agent can call `list_iot_devices` and `get_device_locations`, and the AI SDK feeds the coordinates into your map component one by one. The user watches the map populate in real time. This isn't just for maps. You can build live-updating tables that show device details from `get_device_details` or SIM status from `list_sim_cards`. The data appears as it arrives, creating a responsive feel that's impossible with old-school API calls.

Interactive Usage Portal

Let your users manage their own data usage. An agent armed with `get_billing_cycle_usage` can show them exactly where they stand. If they're getting close to a limit, they see it instantly. When you add controls, the feedback is immediate. A button click can trigger an agent to call `pause_sim_data`, and the UI updates the moment the tool call completes. The user feels in control because they see the effect of their actions without a page reload.

Build with the Vercel AI SDK

This MCP server is built for the AI SDK's streaming architecture. Your agent gets access to 11 tools for managing Hologram.io, from checking SMS with `list_sms_messages` to finding data plans with `list_available_data_plans`. Because tool results stream back, you can build UIs that feel faster and more interactive. It's a perfect match for building user-facing dashboards and control panels on the Vercel stack.

Setup guide

Set up Hologram.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 Hologram.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 Hologram.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 Hologram.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 Hologram.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 Hologram.io MCP in Vercel AI SDK

You'll use the `createMCPClient` function from the AI SDK. Point it to the Vinkius endpoint URL for this server, and then pass the `mcpClient.tools()` output to your `generateText` or `streamText` call. Don't forget to call `mcpClient.close()` when you're done.

Yes. When your agent calls `get_device_locations`, the Vercel AI SDK will stream the results directly into your frontend components. This is ideal for building live maps or location-aware UIs without waiting for the full list to load.

Yes, this setup is designed for it. The MCP client is compatible with the Edge runtime, so you can run your AI logic close to the user for faster responses while still connecting securely to your Hologram.io account.

Real-time UI. Traditional API calls make you wait. With this, tool results stream back as they're generated, letting you build UIs that update live, which is exactly what the AI SDK is good at.

Your connection is proxied through a Vinkius-managed ephemeral sandbox. The server only processes data needed for the tool calls, like device IDs, SIM card numbers, and usage statistics. Your Hologram.io API key is encrypted and never exposed to the AI client.

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