# Browse AI MCP for AI Agents AI Agent Connect > Browse AI MCP lets you trigger web scraping robots and monitor websites directly through your AI agent. You can start tasks, fetch structured data, and manage your scraping schedules without leaving your chat interface. It connects your Browse AI account to your agent so you can handle complex data extraction workflows using natural language. ## Overview - **Category:** data-management - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_8ifM296qnDSBuyeexdFi1mrBAqngOMvNnCKhA6mx/ai-agent-connect - **Tags:** data-extraction, no-code, web-monitoring, structured-data, automated-tasks, data-intelligence ## Description When you need to pull data from a website that's being stubborn about its layout, you usually have to jump between a browser, a scraping tool, and a spreadsheet. This Connector changes that by letting your agent do the heavy lifting for you. Instead of manually setting up every request, you just tell your agent which robot to run and which URL to target. It handles the execution, and then it hands you the clean, structured data you actually need. If you're tracking competitor prices or scraping real estate listings, you can just ask your agent to check the latest results. It's a way to turn web data into a conversational resource. You can find this and thousands of other connections in the Vinkius catalog to keep your tools in sync. It moves the work from a series of clicks into a single conversation, making it way easier to keep your data fresh without the manual overhead. You don't need to worry about selectors or headers once the robot is built; you just focus on what the data means for your business. You can get a single price point or a list of a hundred products just by asking. The agent fetches the info and puts it right in front of you. ## Tools ### create_monitor Create a new monitor schedule for a robot. This helps you automate periodic checks on specific websites. ### remove_webhook Delete robot webhook ### get_user_profile Get account info ### get_robot_details Get robot info ### get_usage_quotas Check credit balance ### get_run_status Check task progress ### list_bulk_operations List bulk task runs ### list_active_monitors List scheduled scrapers ### list_robot_history List past runs ### list_robot_webhooks Get event configs ### trigger_robot_run Start scraping task ### list_robots List all the robots you have approved in your account. Use this to find the right scraper for your current task. ## Prompt Examples **Prompt:** ``` What's the latest price for the 'Modern Lamp' on the target site? ``` **Response:** ``` I've checked the latest run for that robot. Here is the current data: | Product | Price | Status | | :--- | :--- | :--- | | Modern Lamp | $45.00 | In Stock | Would you like me to check any other items? ``` **Prompt:** ``` Run the Amazon tracker on the new product URL. ``` **Response:** ``` Task created! The robot is now processing the URL. I'll let you know as soon as the data is ready. ``` **Prompt:** ``` Show me all my active monitors. ``` **Response:** ``` You currently have 3 active monitors: * **Competitor Price Tracker** (Daily) * **New Listing Alert** (Hourly) * **Real Estate Update** (Every 4 hours) ``` ## Capabilities ### Trigger scraping robots Start specific web extraction tasks on any URL using natural language. ### Fetch captured data Pull structured results from completed tasks directly into your chat. ### Schedule site monitors Create automated schedules to track website changes on a recurring basis. ### Manage bulk extractions Handle multiple data sources in a single run to gather large datasets. ### Check robot metadata View details for all your approved scraping robots in one place. ### Monitor task progress See real-time status updates for active extractions without checking a dashboard. ## Use Cases ### Competitor Price Tracking A marketer asks the agent to run a robot on a competitor's site and then uses get_task to see the latest prices. ### Real Estate Lead Gen A researcher uses create_monitor to track new property listings and asks the agent to summarize the results every morning. ### E-commerce Inventory A developer uses list_tasks to check the status of a large inventory sync and get_bulk_run to see the final count. ### Content Research A writer asks the agent to run a robot on a news site to gather headlines and then retrieves the structured data for a summary. ## Benefits - Get structured data from any website without manual copy-pasting. Use get_task to pull results directly into your chat. - Automate your research with run_robot to trigger extractions on demand. You don't have to leave your workspace to start a job. - Keep track of website changes automatically by using create_monitor. It handles the scheduling so you don't have to check manually. - Manage high-volume data with list_bulk_runs. You can oversee multiple sources at once without getting lost in the dashboard. - Monitor scraper health in real-time with get_system_status. You'll know immediately if there's a queue issue or a system outage. - Organize your scrapers easily with list_robots. You can see all your approved tools in one list to pick the right one for the job. ## How It Works The bottom line is you get a way to run complex web scrapers using only plain English commands. 1. Connect your Browse AI Secret API Key to the Connector. 2. Tell your agent which robot to run or which monitor to create. 3. Get structured data or status updates directly in your chat. ## Frequently Asked Questions **Can Browse AI MCP scrape any website?** Yes, it works with any website that you have already configured as a robot in your Browse AI account. It lets your agent trigger those specific robots for you. **How do I see the data my agent scraped?** Once a task is finished, you can ask your agent to retrieve the data. It will pull the structured results directly into your conversation. **Can I set up new monitors through the agent?** You can use the agent to create new monitor schedules for your existing robots. This helps you automate the tracking of website changes without manual setup. **Is this good for bulk data extraction?** Yes, it includes tools to list and get details for bulk runs. This is ideal for pulling large amounts of data from multiple sources at once. **Does this replace the Browse AI dashboard?** No, it complements it. You still use the dashboard for initial robot setup, but this Connector lets you manage the daily execution and data retrieval through your agent. **How do I connect Browse AI to my AI client?** You just need to subscribe to this Connector and provide your Browse AI Secret API Key. Once connected, your agent can start interacting with your robots. **Can I trigger a data extraction for a specific URL?** Yes! Use the `run_robot` tool with the Robot ID and the target URL (`origin_url`). Your agent will create a new task in Browse AI to extract the data instantly. **How do I retrieve the data once a robot finishes its task?** Simply ask the agent to `get_task` and provide the Task ID. If the status is 'successful', it will return the JSON structure containing all the captured data fields. **Can I list all the robots I have trained in my account?** Yes. Use the `list_robots` tool. It will retrieve all the approved robots currently available in your Browse AI dashboard, including their names and unique IDs. **How do I find my Browse AI Secret API Key?** Log in to your account, navigate to **Account** > **API**, and copy your Secret API Key. **Can I override the origin URL via AI?** Yes! The `trigger_robot_run` tool accepts a `jsonInput` parameter where you can provide an `originUrl` to override the robot's default settings. **How do I check my remaining credits?** Use the `get_usage_quotas` tool to retrieve information about your current subscription and remaining credits directly from the platform.