How can the AI agent run a scrape on a list of product URLs?

First, find your specific scraping Actor ID via `list_actors`. Then, prompt your agent to execute `run_actor`, providing the target URLs formatted as a structured JSON input payload. It returns a 'Run ID'. You can poll this run via `get_run`, and once it succeeds, the agent calls `get_dataset_items` to pull all acquired data straight to your window.

Can the agent interact with run configurations mid-way during crawling?

Yes. If an Apify crawler is currently executing and utilizes a Request Queue, you can instruct your agent to call `push_to_queue`. Doing so dynamically ships new URLs to the active queue instance, extending the current web crawl without needing to stop or restart the Actor.

Can my AI automatically detect scraping timeouts and debug the failure?

Absolutely. Because your agent can track real execution flows with `get_run`, it's aware if it transitions to TIMED-OUT or FAILED states. Subsequently, you can ask the agent to examine the KV Store log outputs ensuring the underlying issue (e.g. captcha block, blocking proxy) is identified immediately.

Apify MCP Server for Vercel AI SDK 10 tools — connect in under 2 minutes

Name: Apify
Availability: InStock
Author: Vinkius

ai-sdk.dev/docs/ai-sdk-core/mcp

Built by Vinkius GDPR 10 Tools SDK

The Vercel AI SDK is the TypeScript toolkit for building AI-powered applications. Connect Apify through the Vinkius and every tool is available as a typed function — ready for React Server Components, API routes, or any Node.js backend.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

typescript

import { createMCPClient } from "@ai-sdk/mcp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

async function main() {
  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      // Your Vinkius token — get it at cloud.vinkius.com
      url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    },
  });

  try {
    const tools = await mcpClient.tools();
    const { text } = await generateText({
      model: openai("gpt-4o"),
      tools,
      prompt: "Using Apify, list all available capabilities.",
    });
    console.log(text);
  } finally {
    await mcpClient.close();
  }
}

main();

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Apify MCP Server

Connect your Apify workspace to your AI agent and seamlessly direct full-stack web scraping and data extraction workflows through natural conversation.

The Vercel AI SDK gives every Apify tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 10 tools through the Vinkius and stream results progressively to React, Svelte, or Vue components — works on Edge Functions, Cloudflare Workers, and any Node.js runtime.

What you can do

Discover & Run Actors — Browse all scraper bots (Actors) available in your account. Fire them off asynchronously or synchronously for fast, targeted scraping
Extract Datasets — Pull robust structured data formats out of completed runs. Retrieve detailed JSON records directly into the agent's context window
Fetch Key-Value Stores — Programmatically read snapshots, cached HTML pages, or screenshots from the Apify Key-Value repositories mapped to a run
Job Control & Scalability — Stop hanging scraper jobs, queue new dynamic URLs mid-run, or inspect deep usage analytics, compute units, and webhooks limits

The Apify MCP Server exposes 10 tools through the Vinkius. Connect it to Vercel AI SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Apify to Vercel AI SDK via MCP

Follow these steps to integrate the Apify MCP Server with Vercel AI SDK.

Install dependencies

Run npm install @ai-sdk/mcp ai @ai-sdk/openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the script

Save to agent.ts and run with npx tsx agent.ts

Explore tools

The SDK discovers 10 tools from Apify and passes them to the LLM

Why Use Vercel AI SDK with the Apify MCP Server

Vercel AI SDK provides unique advantages when paired with Apify through the Model Context Protocol.

TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box

Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime — same Apify integration everywhere

Built-in streaming UI primitives let you display Apify tool results progressively in React, Svelte, or Vue components

Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency

Apify + Vercel AI SDK Use Cases

Practical scenarios where Vercel AI SDK combined with the Apify MCP Server delivers measurable value.

AI-powered web apps: build dashboards that query Apify in real-time and stream results to the UI with zero loading states

API backends: create serverless endpoints that orchestrate Apify tools and return structured JSON responses to any frontend

Chatbots with tool use: embed Apify capabilities into conversational interfaces with streaming responses and tool call visibility

Internal tools: build admin panels where team members interact with Apify through natural language queries

Apify MCP Tools for Vercel AI SDK (10)

These 10 tools become available when you connect Apify to Vercel AI SDK via MCP:

abort_run

Any data already scraped and pushed to the dataset is preserved. The run status changes to ABORTED. Use this to stop runaway scrapes or when sufficient data has been collected. Graceful shutdown depends on the actor implementation. Abort an active Apify actor run

get_account_limits

Essential for monitoring consumption and avoiding overage charges. Check Apify account subscription limits and compute unit usage

get_dataset_items

The datasetId is found in the run object (defaultDatasetId). Supports pagination via limit (max items per page) and offset (starting position). Returns an array of JSON objects containing the scraped data fields. Use limit=1000 for bulk downloads. Export structured JSON data from an Apify dataset

get_key_value_store

Key-value stores hold arbitrary data like screenshots (OUTPUT), configuration files, or intermediate results. The storeId comes from the run object (defaultKeyValueStoreId). Common keys include "OUTPUT", "INPUT", and "SCREENSHOT". Retrieve an item from an Apify actor key-value store

get_run

Poll this endpoint to track long-running scrapes. Check the status and metadata of a specific Apify actor run

list_actors

Includes owned actors and those from the Apify Store that have been saved. Each entry contains the actorId, name, description, and default run configuration. Use the actorId to trigger runs. List all accessible actors in the Apify account

list_webhooks

RUN.SUCCEEDED, ACTOR.RUN.FAILED), target URLs, and associated actor IDs. Webhooks enable event-driven architectures by notifying external systems when actor runs complete or fail. List all configured webhooks in the Apify account

push_to_queue

Pass the queueId (from the run object) and a JSON string array of request objects, e.g., [{"url":"https://...","uniqueKey":"..."}]. This enables dynamic crawling where new pages are discovered and added during execution. Dynamically push new URLs to an active Apify request queue

run_actor

Pass the actorId (e.g., "apify/web-scraper" or a custom ID) and a JSON string with the input configuration (start URLs, proxy settings, max pages, etc.). Returns immediately with a runId. Use ap.get_run to poll for completion and ap.get_dataset_items to retrieve extracted data. Start an Apify actor asynchronously with custom JSON input

run_actor_sync

run_actor but waits for the actor to finish before returning. The response includes the full run object with defaultDatasetId for immediate data retrieval. Best for short-lived actors (under 5 minutes). For long-running scrapes, use the async ap.run_actor instead. Run an Apify actor and block until completion (synchronous)

Example Prompts for Apify in Vercel AI SDK

Ready-to-use prompts you can give your Vercel AI SDK agent to start working with Apify immediately.

"List all the Apify actors available on my account."

"Verify the status of run 'qKpwH9LgC3r0Xm' and show me its final dataset if finished."

"How are our compute usage limits tracking this current month on Apify?"

Troubleshooting Apify MCP Server with Vercel AI SDK

Common issues when connecting Apify to Vercel AI SDK through the Vinkius, and how to resolve them.

createMCPClient is not a function

Install: npm install @ai-sdk/mcp

Apify + Vercel AI SDK FAQ

Common questions about integrating Apify MCP Server with Vercel AI SDK.

How does the Vercel AI SDK connect to MCP servers?

Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.