How to Use the Liftoff MCP in Vercel AI SDK

Pull live Liftoff performance data into your Vercel AI SDK frontends for instant, streaming analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liftoff MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Liftoff data for Vercel AI SDK

Feed your UI with live metrics directly from the Liftoff API. By passing `get_spend_metrics` into your Vercel AI SDK tool definitions, you push performance data straight to the user without waiting for manual refresh cycles. Your React components update the moment the stream resolves. It's built for low-latency dashboards where the data needs to be as fresh as the AI's response.

Asynchronous reporting in Vercel AI SDK

Handle heavy data loads without blocking the main event loop. Trigger a report with `request_performance_report`, then use `get_report_status` to track progress while keeping the UI responsive for the end user. Once the status returns as complete, `download_report_results` fetches your CSV data. It keeps your Edge Functions lean and ensures your app doesn't hang while the backend processes large files.

Asset and campaign discovery

Map your entire ad structure by querying `list_liftoff_campaigns` and `list_liftoff_creatives` within your application flow. You gain visibility into active assets without leaving your code environment. These tools return raw metadata that you can pipe directly into your client-side state. It's the fastest way to build custom campaign browsers that feel native to your specific business logic.

Setup guide

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

You handle auth via the standard Vercel AI SDK authProvider. Keep your endpoint tokens in environment variables and never expose them in client-side code.

Yes. Since the MCP server provides direct tool output, you can pipe the result of any function like `get_spend_metrics` into the streamText response.

All campaign metadata and spend logs are kept behind your server-side auth. The Vercel AI SDK environment only receives the data you explicitly return from your tools.

It does. The standard HTTP transport works with edge runtimes as long as your network configuration permits outbound requests to the Liftoff API.

You should implement a caching layer in your server-side code. Don't call `list_liftoff_apps` on every render; store the result and only refresh when necessary.

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