How to Use the GrowingIO MCP in Vercel AI SDK

Q: How do I pass custom variables from Vercel AI SDK to GrowingIO?

You fetch existing schemas using listvariables and then let your Vercel AI SDK agent map incoming user metadata to the correct tracked variables. This ensures your event payloads match your analytics setup.

Get live China product analytics streaming straight to your React components with the GrowingIO MCP Server for 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 GrowingIO MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Funnel UI with Vercel AI SDK

The `get_funnel` tool pulls conversion steps from GrowingIO to build real-time visual funnels in your Next.js frontend. When your user asks about drop-off rates, the Vercel AI SDK streams the raw conversion numbers directly into a clean UI component without making them wait for a full page reload. This integration bypasses slow backend polling by letting your AI client fetch and render user flow data on the fly. You get immediate visual feedback on funnel performance while keeping your Edge Functions fast and light.

Instant Event Debugging in Your UI

The `get_event` and `list_events` tools query specific user actions to let you inspect raw tracking data inside your application. Your AI client pulls these event definitions dynamically, showing your developers exactly what triggers are firing on the frontend. Using these tools with the Vercel AI SDK means you don't have to build custom dashboards just to check event schemas. The raw event payloads render instantly in your chat interface, making debugging your China-market tracking setup a two-second job.

Live Segment Metrics Rendering

The `get_metrics` and `list_segments` tools pull aggregate user behavior data directly from your project. Your React app can render these metrics on a live dashboard as your AI client fetches them, displaying user counts and active segments side-by-side. By combining these GrowingIO tools with the Vercel AI SDK, you build an interface where marketing teams ask for a segment and watch the user counts populate in real-time. It cuts out the middleman and keeps your database queries securely scoped.

Setup guide

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

Use the Vercel AI SDK's streamText function to render partial data chunks while the GrowingIO MCP Server fetches deep funnel metrics. This keeps your React UI responsive even when pulling heavy analytical datasets across regions.

Yes. The GrowingIO MCP Server connects via standard HTTP or SSE, making it lightweight enough to run within Vercel AI SDK edge environments without hitting execution limits.

You fetch existing schemas using `list_variables` and then let your Vercel AI SDK agent map incoming user metadata to the correct tracked variables. This ensures your event payloads match your analytics setup.

No. You can let the AI generate standard JSON views or use pre-built charts that accept the raw output from `get_event` and `get_metrics`.

Vinkius runs the MCP Server in an isolated V8 sandbox, ensuring that your raw GrowingIO segment lists and funnel metrics are never cached or exposed to third-party LLM providers. All data transfers use encrypted ephemeral tunnels that self-destruct after the execution finishes.

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