An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Apify to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get structured data and automate complex web workflows.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Apify.

  1. 01

    Abort run

    Stop an active Apify actor run. Use this when a scrape is running too long or when you've collected enough data and need a graceful shutdown.

  2. 02

    Get dataset items

    Export structured JSON data from an Apify dataset. You can pull the scraped data fields, supporting pagination so you can download large amounts of records.

  3. 03

    Get account limits

    Check your Apify account subscription limits and compute unit usage. This is essential for monitoring consumption and avoiding overage charges.

  4. 04

    Get key value store

    Retrieve an item from an Apify actor key-value store. This capability lets you pull arbitrary data like screenshots, configuration files, or intermediate results using a specific store ID.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Apify.

  1. 05

    Get run

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

  2. 06

    List actors

    List all accessible actors in the Apify account. This capability shows you all available scraper bots, including owned and public templates, and provides the IDs needed to start a run.

  3. 07

    List webhooks

    List all configured webhooks in the Apify account. Webhooks let you know when actor runs complete or fail, which is useful for event-driven systems.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Apify.

  1. 08

    Push to queue

    Dynamically push new URLs to an active Apify request queue. This enables continuous crawling by adding newly discovered pages to a running job.

  2. 09

    Run actor

    Start an Apify actor asynchronously with custom JSON input. Pass the actor ID and input configuration to trigger a scrape, which returns a run ID you can track later.

  3. 10

    Run actor sync

    Run an Apify actor and wait until it finishes before returning. Use this for short-lived scrapes (under five minutes) when you need the data immediately.

Real work

What teams actually run

01

Competitive Price Monitoring

You need to track product prices across multiple competitor sites. The AI runs a dedicated actor and pulls the resulting dataset into a table for comparison.

02

Gathering Technical Specs

You are building a database of product specifications. The AI runs a scraper to pull structured data fields, like dimensions and materials, from product pages.

03

Monitoring Site Health

You want to ensure a website is updating its content. The AI can run a scrape and retrieve screenshots from the key-value store for visual verification.

04

Large-Scale Data Collection

You need to pull thousands of records. The AI runs the job asynchronously and then uses pagination to download the entire dataset in chunks.

Automate a task

Put Apify to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Apify works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Apify to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

919ms average. Fast in production.

Apify is checked daily against the live service.

Daily averagePeak 1004ms
Oct 3Today
Fastest day
745ms
Slowest day
1004ms
14-day trend
Stable-2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Apify, so you can see the experience inside your AI.

It does not authenticate your account with Apify. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Apify Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_kyOCHu4Rvz1CsEZ7ViQMTOM5deCOQwTatWoMs4PP/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Apify capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "apify-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_kyOCHu4Rvz1CsEZ7ViQMTOM5deCOQwTatWoMs4PP/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Apify in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Apify owners hand off.

This MCP is built for professionals who need reliable, large-scale data extraction. If your job involves gathering structured information from websites, this capability lets you automate the entire process using natural language commands.

  • 01

    Data Engineers

    Use this to trigger scheduled extraction logic and map Apify objects within a conversational QA check.

  • 02

    Market Researchers

    Command the AI to scrape product prices using Apify actors and compile the resulting JSON datasets into readable markdown tables.

  • 03

    AI Developers

    Augment your agent's real-time capabilities by feeding it massive structured site data freshly scraped via headless browsers.

FAQ

Questions Apify owners ask.

  • 01

    Is this MCP for all types of web scraping?

    It connects to the Apify platform, which supports full-stack web scraping. You can run various 'Actors'—which are specialized scraper bots—to extract data from different types of websites.

  • 02

    Can I handle very large datasets?

    Yes. The get_dataset_items capability supports pagination, allowing you to pull structured JSON data in large batches, up to 1000 items per page.

  • 03

    What if my scrape job fails or runs too long?

    You can use the get_run capability to check the job's status. If it's running wild, you can use abort_run to stop it immediately.

  • 04

    Does this MCP require me to know coding?

    No. You interact with the entire system using natural conversation. Your AI agent handles the underlying complexity of running the scrapers and extracting the data.

  • 05

    How do I check my usage limits?

    Use the get_account_limits capability. This lets you monitor your compute unit usage and proxy bandwidth, helping you avoid overage charges.

  • 06

    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.

  • 07

    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.

  • 08

    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.

Explore

More in Ship It

Suggestions

Connect Apify to Claude, Cursor, ChatGPT & more