# Apify MCP for AI Agents AI Agent Connect

> Apify lets your AI agent run web scrapers, extract structured data, and manage browser tasks. It connects your Apify workspace to any MCP-compatible client so you can command complex data extraction workflows using natural language instead of writing custom scripts.

## Overview
- **Category:** ship-it
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_kyOCHu4Rvz1CsEZ7ViQMTOM5deCOQwTatWoMs4PP/ai-agent-connect
- **Tags:** web-automation, data-extraction, proxy-services, headless-browser, datasets, api-integration

## Description

Stop fighting with headless browser configurations and proxy rotations. This Connector gives your agent the ability to interact with your full Apify workspace directly. Instead of manually setting up actors or checking logs in a dashboard, you can just tell your agent to go grab a list of products from a specific site or pull the latest pricing data. It handles the heavy lifting of web scraping while you focus on what to do with the data. If you're already using Vinkius to manage your AI Connectors, adding this is the quickest way to turn your AI into a high-powered data gathering machine. You can start a scrape, check its progress, and grab the final JSON results without ever leaving your chat window. It's about moving from 'how do I scrape this' to 'give me the data from this site.'

## Tools

### abort_run
Stop an active Apify actor run. Use this to end runaway scrapes while preserving already collected data.

### get_account_limits
Check your Apify account subscription limits. Monitor compute unit usage to avoid overage charges.

### get_dataset_items
Export structured JSON data from an Apify dataset. Use limit and offset for paginated bulk downloads.

### get_key_value_store
Retrieve an item from an Apify actor key-value store. This is useful for getting screenshots or config files.

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

### list_actors
List all accessible actors in your Apify account. See both owned actors and saved public templates.

### list_webhooks
List all configured webhooks in your account. See target URLs and associated actor IDs for event-driven tasks.

### push_to_queue
Dynamically push new URLs to an active Apify request queue. This lets you add discovered pages mid-run.

### run_actor_sync
Run an Apify actor and block until completion. This is best for short-lived tasks under five minutes.

### run_actor
Start an Apify actor asynchronously with custom JSON input. Use this for large scrapes to get a run ID back.

## Prompt Examples

**Prompt:** 
```
List all the Apify actors available on my account.
```

**Response:** 
```
I've scanned your Apify actor catalog. You possess 3 main actors: 'ecommerce-spider-v1' and two public templates 'google-search-scraper' and 'instagram-scraper'. Shall I print their base configurable inputs?
```

**Prompt:** 
```
Verify the status of run 'qKpwH9LgC3r0Xm' and show me its final dataset if finished.
```

**Response:** 
```
I checked run `qKpwH9LgC3r0Xm`. Its current status is `SUCCEEDED`. The run consumed 0.045 Compute Units. I have successfully downloaded the associated dataset (`ds_8aBxP_...`) which yielded 302 product profiles. I'm injecting the top 5 parsed items below.
```

**Prompt:** 
```
How are our compute usage limits tracking this current month on Apify?
```

**Response:** 
```
I pulled your overall compute records. Right now on the 'Scale' plan, your account used 82 out of 100 Compute Units (CU). You've consumed significant resources on proxy bandwidth (1.8TB/2TB) leading to roughly 80% usage threshold. I recommend holding further massive scraped runs until renewal happens on the 10th.
```

## Capabilities

### Pull structured JSON
Get clean data from finished scraper runs directly into your agent's context.

### Kill runaway scrapes
Stop active jobs immediately to save on compute units and costs.

### Queue new URLs
Add new links to a scraper while it is already running to expand your crawl.

### Monitor account usage
Check your remaining compute units and subscription limits in real time.

### Fetch screenshots
Retrieve visual snapshots or configuration files from your actor runs.

## Use Cases

### Competitive Price Tracking
A researcher asks the agent to scrape a list of electronics from a retail site. The agent runs the actor and returns a markdown table of prices.

### Dynamic Crawling
A dev needs to scrape a site where links are generated on the fly. The agent finds the links and pushes them to the queue while the run is active.

### Data Enrichment
An engineer uses the agent to pull structured product profiles from a completed run to update a local database.

### Resource Management
An ops lead asks the agent to check how many compute units are left for the month to plan the next big data pull.

## Benefits

- Stop manual data entry by letting your agent pull JSON records directly into your workspace.
- Control your costs by monitoring compute units and stopping runaway jobs instantly.
- Expand your reach by pushing new URLs to active queues while a scraper is already running.
- Get visual proof of your scrapes by pulling screenshots from key-value stores into your chat.
- Save time on setup by using pre-built actors instead of writing custom scraping logic from scratch.

## How It Works

The bottom line is you get a conversational interface for your entire Apify scraping infrastructure.

1. Subscribe to the Connector and provide your Personal Apify API Token.
2. Connect the Connector to your preferred AI client like Claude or Cursor.
3. Command your agent to find actors, start runs, and pull datasets via chat.

## Frequently Asked Questions

**Can I use the Apify MCP to scrape social media sites?**
Yes, you can use your agent to run specific actors designed for social platforms. The Connector allows your agent to trigger these runs and pull the resulting data back into your chat.

**Does the Apify MCP support bypassing bot detection?**
Yes, because it connects to your Apify workspace, it uses Apify's proxy networks and browser management to handle bot detection for you.

**How do I see how many compute units I have left with Apify MCP?**
You can simply ask your agent to check your account limits. It will pull your current subscription data and tell you how much of your monthly quota remains.

**Can my agent find new URLs while a scrape is running?**
Yes, the Connector supports pushing new URLs to an active queue. This allows your agent to manage dynamic crawls where new pages are discovered as the scraper moves.

**Is it possible to get screenshots of a website using the Apify MCP?**
Yes, you can ask your agent to retrieve items from your key-value store. This includes visual snapshots and configuration files from your completed runs.

**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.