How to Use the Apify MCP in Vercel AI SDK

Q: How do I run Apify actors inside a Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the client using the HTTP transport. Pass the tools directly into streamText or generateText so your agent can trigger runs and read datasets.

Feed real-time web scraping datasets directly into your React components using the Vercel AI SDK and this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run web scrapers from Vercel AI SDK on the fly

The `run_actor` tool lets your agent spin up any Apify actor directly from your edge functions. You don't have to write custom API endpoints or handle webhook listeners to start a scrape. Your application triggers the actor run and monitors the progress. By passing parameters dynamically, your frontend lets users kick off complex extraction tasks with a single prompt.

Stream scraped data into your UI live

The `get_dataset_results` tool pulls raw JSON data from finished or active scraping runs directly into your application context. Instead of forcing users to wait for a full extraction to finish, your agent feeds the incoming rows straight into React state. This setup avoids long loading spinners on the frontend. The data populates your interface row by row as the Vercel AI SDK processes the incoming stream from the MCP Server.

Inspect active jobs and data stores

The `get_run_details` and `list_datasets` tools give your agent complete visibility over your scraper pipeline status. Your agent checks whether an extraction job is still running, failed, or ready for consumption without manual API polling. You write the logic to fetch the latest state, and the AI handles the routing. This keeps your edge functions light because you don't need to bundle heavy third-party SDKs to read from your storage.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using the HTTP transport. Pass the tools directly into `streamText` or `generateText` so your agent can trigger runs and read datasets.

Yes. Your agent starts the execution and polls for updates. Because edge functions have timeout limits, you should design the agent to trigger the run and check back later rather than holding a connection open.

The server passes your credentials directly to the platform API. If you hit rate limits, the API returns standard status codes, which your agent can read and handle using standard retry patterns.

You pass your API token securely through the MCP client initialization. The SDK routes all tool calls through our secure gateway, keeping your credentials hidden from the client browser.

Your scraped payload goes directly from the platform to your application via a secure, ephemeral V8 sandbox. No data is cached or stored on our servers, keeping your extraction pipelines completely isolated.

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