How to Use the Hevo Data (ETL & Data Pipeline) MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to Hevo Data (ETL & Data Pipeline)?

Install @ai-sdk/mcp and create the client using createMCPClient. Pass your Vinkius endpoint URL to the HTTP transport layer. Then inject mcpClient.tools() into your generation call.

Q: Can the Vercel AI SDK stream Hevo Data (ETL & Data Pipeline) workflows into Next.js?

Yes. Your application calls listworkflows through the client. The SDK streams the workflow definitions directly into your React components as the AI processes the response.

Q: Do I need OAuth to check pipeline models?

You can pass an authProvider to the MCP setup if your app requires user-level authentication. Otherwise, the Vinkius endpoint token handles access when the AI calls listmodels.

Stream Hevo pipeline metrics directly into your React frontend using the 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 Hevo Data (ETL & Data Pipeline) MCP to Vercel AI SDK

Create your Vinkius account to connect Hevo Data (ETL & Data Pipeline) 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 Hevo Data (ETL & Data Pipeline) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Pipeline Status

`list_pipelines` and `get_pipeline` let your Vercel AI SDK application pull real-time ETL statuses straight into the UI. You don't need a loading spinner while the server checks if a sync failed. The agent queries the Hevo API and streams the pipeline metadata back to the client instantly. Your users watch the pipeline grid populate with current sync states as the data arrives.

Render Destination Grids Fast

`list_destinations` gives your React frontend the exact warehouse targets your Hevo account is hitting. The Vercel AI SDK handles the tool execution on the server and pipes the JSON directly into your UI components. Your end users see the connection status of every data warehouse without waiting for a batch refresh. You pass the tools to `streamText`, and the interface updates the moment the server responds.

Build Usage Dashboards via MCP Server

`get_usage` feeds real-time Hevo billing and event consumption metrics into your custom dashboards. You connect the MCP Server to your Vercel edge function using standard HTTP transports. When a user asks for their monthly event count, the AI calls the tool and streams the numbers back. They get the exact row count and event quota usage without ever logging into the Hevo console.

Setup guide

Set up Hevo Data (ETL & Data Pipeline) 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 Hevo Data (ETL & Data Pipeline) 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 Hevo Data (ETL & Data Pipeline) 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 Hevo Data. 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 Hevo Data (ETL & Data Pipeline) 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 Hevo Data (ETL & Data Pipeline) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and create the client using `createMCPClient`. Pass your Vinkius endpoint URL to the HTTP transport layer. Then inject `mcpClient.tools()` into your generation call.

Yes. Your application calls `list_workflows` through the client. The SDK streams the workflow definitions directly into your React components as the AI processes the response.

The server throws an HTTP 429 error back to your application. You handle the exception in your edge function and render the error state in the frontend. Always close the connection to prevent hanging requests.

You can pass an `authProvider` to the MCP setup if your app requires user-level authentication. Otherwise, the Vinkius endpoint token handles access when the AI calls `list_models`.

The V8 Isolate Sandbox destroys the execution environment the moment the request finishes. Your edge functions read the pipeline IDs and destination schemas, but nothing persists on Vinkius. The connection drops immediately.

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