How to Use the Airbyte MCP in Vercel AI SDK

Q: How do I stream Airbyte sync jobs in a Next.js app using Vercel AI SDK?

Install @ai-sdk/mcp and initialize the client with the Vinkius endpoint. Pass the tools from mcpClient.tools() into streamText to let your model call listjobs dynamically. Always remember to call mcpClient.close() inside your edge route to prevent memory leaks.

Q: Can Vercel AI SDK handle OAuth for Airbyte sources?

Yes, the SDK supports this through the authProvider configuration. When your agent calls getsource or listsources, Vinkius routes the request using the secure user token. This keeps credentials out of your frontend codebase entirely.

Q: How do I limit which Airbyte tools Vercel AI SDK can access?

You filter the tools array returned by mcpClient.tools() before passing them to your generation function. For example, if you only want read-only monitoring, omit everything except listconnections and listjobs. This keeps your edge functions lightweight and secure.

Stream Airbyte pipeline metrics directly to your Next.js UI in real-time using 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 Airbyte MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Airbyte sync statuses live with Vercel AI SDK

Stop making your users stare at a blank loading spinner while waiting for data pipeline updates. By combining this MCP Server with Vercel's streaming capabilities, your interface displays live synchronization updates the millisecond they happen. The `list_jobs` tool fetches the raw execution history, and the SDK streams the state changes directly into your React components. You hook up `list_connections` to check if a sync is running, then pipe that data directly to the frontend. Because this runs on edge functions, your users get instant feedback on their data pipelines without a middleman server slowing things down.

Map Airbyte sources dynamically on the edge

Your application can now inspect data origins on the fly. When a user asks what databases are connected, Vercel AI SDK calls `list_sources` and maps the active schemas directly into your UI. Your client handles the raw JSON payload and formats it into clean, readable cards without blocking the main thread. Using `get_source` allows the model to drill down into specific database credentials and connection parameters. It gives your users a clear picture of their ingestion architecture without leaving your custom dashboard.

Troubleshoot failing Airbyte destinations in real-time

When a sync breaks, your interface shouldn't just show a generic error message. This MCP Server exposes `list_destinations` so your Vercel AI SDK client can instantly identify where the data flow is blocked. Your agent reads the configuration error, identifies the broken warehouse, and suggests the exact fix. Calling `get_connection` lets the model examine the exact path from source to target. Since the SDK streams the troubleshooting steps line-by-line, your users watch the diagnosis unfold live on their screen.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client with the Vinkius endpoint. Pass the tools from `mcpClient.tools()` into `streamText` to let your model call `list_jobs` dynamically. Always remember to call `mcpClient.close()` inside your edge route to prevent memory leaks.

Yes, the SDK supports this through the `authProvider` configuration. When your agent calls `get_source` or `list_sources`, Vinkius routes the request using the secure user token. This keeps credentials out of your frontend codebase entirely.

You filter the tools array returned by `mcpClient.tools()` before passing them to your generation function. For example, if you only want read-only monitoring, omit everything except `list_connections` and `list_jobs`. This keeps your edge functions lightweight and secure.

No, the SDK process is completely asynchronous and runs on Vercel's edge network. When the model invokes `list_workspaces`, the HTTP transport handles the request off the main thread. Your UI remains fully responsive while the workspace metadata loads.

This server runs inside a zero-trust V8 Isolate Sandbox on Vinkius, meaning your database passwords and API keys are never written to persistent storage. Every time your SDK calls `get_connection` to inspect a pipeline, the session is ephemeral and wiped instantly after execution.

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