# Apify MCP for AI Agents AI Agent Connect > Apify lets you manage your cloud automation and web scraping workflows through a natural conversation with your AI agent. Instead of digging through technical consoles, you can audit actors, monitor task execution, and pull dataset items instantly. It turns complex scraping infrastructure into a manageable conversation. ## Overview - **Category:** friends-mcp - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_pvv6MX9ZP8hnkCba86SJURXFBwAhkV4b6QXmWdj1/ai-agent-connect - **Tags:** data-extraction, serverless-actors, web-automation, data-scraping, api-integration, structured-data ## Description Imagine you're running dozens of web scrapers and data pipelines simultaneously. Usually, checking their status means jumping between tabs, filtering logs, and hunting for specific dataset entries. With this Connector, your AI agent takes over that manual labor. You can ask it to check if a specific scraper is still running or pull the latest results from a dataset without ever leaving your chat interface. It treats your entire Apify ecosystem as a workspace where you can query schedules, webhooks, and actor metadata on the fly. It's about moving from manual monitoring to high-level oversight. By connecting this to your workflow via the Vinkius catalog, you get a dedicated operator that keeps your data flowing and your automation running smoothly. You stop being a console operator and start being a strategist. ## Tools ### list_actor_runs List recent actor executions ### list_actor_tasks List configured actor tasks ### get_dataset_results Get items from a dataset ### get_run_details Get details for a specific run ### run_actor Trigger an actor run ### list_actors List every actor in your account. You can use this to get a bird's-eye view of your entire scraper fleet. ### list_datasets List all your available datasets. Use this to see where your scraped data is being stored. ## Prompt Examples **Prompt:** ``` List all my actors. ``` **Response:** ``` I've retrieved your actors. You have 5 active actors, including 'Website Content Crawler' and 'Google Maps Scraper'. Which one would you like to audit for recent runs? ``` **Prompt:** ``` Show me the last 5 runs for actor ID xxxx. ``` **Response:** ``` I've found the last 5 runs. The most recent one was completed successfully in 2 minutes. Two other runs had warnings. Would you like the full log details? ``` **Prompt:** ``` Get items from dataset ID yyyy. ``` **Response:** ``` I've retrieved the data from that dataset. It contains 50 items related to 'Competitor Pricing'. I can summarize the top findings or provide the full list. ``` ## Capabilities ### Audit actor metadata Get the status and descriptions of all your scrapers in one go. ### Monitor task performance See which runs succeeded or failed without checking logs manually. ### Extract dataset items Pull specific data points out of your finished automation jobs. ### Manage automation schedules View and organize when your different web scrapers are set to trigger. ### Track webhook configurations Keep tabs on your external data triggers and integrations. ### Query key-value stores Access your stored configuration data quickly through natural language. ## Use Cases ### Audit a failing scraper A data engineer notices a scraper is stalling. They ask the agent to list_runs for that actor to see if it's hitting a specific error code. ### Quick data extraction A growth lead needs the latest competitor prices. They ask the agent to get_dataset_items for a specific dataset to get the latest numbers. ### Workflow overview An ops manager wants to know what's running today. They ask the agent to list_tasks and list_schedules to see the full plan. ### Actor setup check A developer wants to see if their new scraper is live. They ask the agent to list_actors and get_actor to verify the status. ## Benefits - Stop manual log checking by using list_runs to see which scrapers succeeded or failed instantly. - Pull data faster with get_dataset_items to grab specific results without navigating complex filters. - Keep your automation organized by using list_schedules to see every planned trigger in one view. - Audit your entire fleet with list_actors to see what's running and what's idle across your account. - Manage configurations easily with list_key_value_stores to see how your actors are set up. - Track your data flow with list_webhooks to ensure your external integrations are active and correct. ## How It Works The bottom line is you get a real-time command center for your cloud scraping and automation workflows. 1. Subscribe to this Connector on Vinkius. 2. Add your Apify API Key to the configuration. 3. Ask your agent to list actors or check dataset items. ## Frequently Asked Questions **How can I use the Apify MCP to manage my scrapers?** You connect the Connector to your AI client and can then use natural language to list your actors, check their run history, and manage your schedules without leaving your chat. **Can I see my scraping success rates with Apify MCP?** Yes, you can ask your agent to show recent runs for any specific actor. It will pull the execution data so you can see what succeeded and what failed. **How do I get my scraped data into my agent using Apify MCP?** Your agent can pull items directly from your Apify datasets. Just tell the agent which dataset you want to see, and it will retrieve the items for you. **Does Apify MCP help with scheduling my web scraping tasks?** It allows your agent to view all your active schedules. You can use it to verify when tasks are set to trigger and keep your automation on track. **Can I check my webhooks with Apify MCP?** Yes, you can ask the agent to list your webhooks. This helps you ensure your data is being sent to the correct external endpoints. **How does Apify MCP make data engineering easier?** It removes the need for manual log auditing. You can query your actor metadata, task status, and dataset contents through a single conversation. **How do I find my Apify API Key?** Log in to your [**Apify Console**](https://console.apify.com/account/integrations), and you will find your API Token under the **Integrations** tab. Copy and paste it below. **Can the agent check the results of a scrape?** Yes. Use the `get_dataset_items` tool providing the Dataset ID. Your agent will retrieve the items from the cloud storage, allowing you to audit the output instantly. **Is it possible to list actor runs via the agent?** Yes. The `list_runs` tool allows your agent to retrieve the history of executions for any specific actor, including durations and final statuses. **Can I provide input parameters when running an actor?** Yes! Use the `run_actor` tool and provide the optional `input` JSON object to configure specific scraper settings for that run. **How do I see the items collected in a dataset?** Run the `get_dataset_results` query with your Dataset ID. The agent will retrieve the data records, which you can then ask the AI to summarize or analyze. **Is it possible to check the status of a specific actor run?** Absolutely. Use the `get_run_details` tool and provide the Run ID. Your agent will retrieve the status (RUNNING, SUCCEEDED, FAILED) and metadata for that specific execution.