# ScreenshotOne MCP for AI Agents AI Agent Connect > ScreenshotOne lets your AI agent grab high-quality website screenshots, generate PDFs from URLs, and pull page metadata. It turns visual auditing into a natural conversation, allowing you to capture specific elements, full pages, or custom viewports without opening a browser. ## Overview - **Category:** productivity - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_JUwwYa83yWRRMbOnbxUmQsFRB6tFeXnZOYxfQrXu/ai-agent-connect - **Tags:** screenshot-api, pdf-generation, web-automation, visual-auditing, image-processing ## Description Let your AI agent handle your visual auditing and website capturing with ScreenshotOne, a reliable way to get high-quality screenshots. By connecting ScreenshotOne to your agent, you turn complex capturing tasks into a natural conversation. Your agent can instantly take full-page screenshots, generate PDFs from URLs, and pull page metadata without you ever touching a browser. Whether you are monitoring site changes or archiving visual content, your agent acts as a real-time visual archiver to keep your records clean. Finding this in the Vinkius catalog makes it easy to plug these capabilities into your current workflow. ## Tools ### get_page_metadata Get metadata for a website like the title and size without capturing. This lets you pull info quickly. ### take_element_screenshot Take a screenshot of a specific CSS element. It is useful for checking if a single button or header looks correct. ### take_screenshot Take a screenshot of a URL. Use this for a standard capture of a webpage as it appears normally. ### take_viewport_screenshot Take a screenshot with a specific viewport size. This helps you see how a site looks on mobile or tablet. ### generate_pdf Generate a PDF from a URL. This turns any webpage into a shareable document instantly. ### take_full_page_screenshot Take a full-page screenshot of a URL. This captures the entire height of a website in one go. ## Prompt Examples **Prompt:** ``` Take a screenshot of https://vinkius.com. ``` **Response:** ``` I've captured the screenshot for you! You can access the high-quality image via the provided URL. Would you like a full-page capture or a PDF version as well? ``` **Prompt:** ``` Capture the full page of https://github.com/vinkius. ``` **Response:** ``` Full-page capture initiated! I've retrieved the image showing the entire GitHub profile. It includes all repositories and contributions. Would you like the direct link? ``` **Prompt:** ``` Show metadata for https://www.google.com. ``` **Response:** ``` I've retrieved the metadata for Google. The site title is 'Google' and the page size is approximately 50KB. Would you like me to take a screenshot now? ``` ## Capabilities ### Capture specific CSS elements Take a photo of a specific part of a page like a button or header. ### Get page titles and sizes Pull site metadata instantly without having to render the whole page. ### Convert URLs to PDFs Turn any webpage into a professional PDF document for easy sharing. ### Grab full-page captures Capture a website from top to bottom to see the entire layout. ### Set custom viewports See how a site looks on specific screen sizes like mobile or tablet. ## Use Cases ### Visual Regression Testing A QA engineer asks the agent to check if the 'Submit' button is still blue on mobile. The agent uses take_viewport_screenshot to verify the UI. ### Client Deliverables A designer needs to send a mockup of a live site. They ask the agent to 'Make a PDF of the homepage,' and the agent uses generate_pdf. ### Rapid Content Archiving An archivist needs to save 50 URLs. They tell the agent to 'Take full-page screenshots of these links' and the agent processes the list. ### Competitor Metadata Scraping An ops lead needs to know the titles of 100 competitor pages. The agent uses get_page_metadata to gather the info quickly. ## Benefits - Stop manual browser resizing by using take_viewport_screenshot to set exact dimensions for mobile or tablet views. - Create shareable documents instantly with generate_pdf instead of printing pages to your local machine. - Audit specific UI components quickly using take_element_screenshot to ignore the rest of the page noise. - Save time on data gathering with get_page_metadata to pull titles and sizes without full page renders. - Keep accurate records of site changes by using take_full_page_screenshot to capture entire landing pages. - Get direct image links for every capture, making it easy to share assets with your team immediately. ## How It Works The bottom line is you get high-quality visual captures and documents through natural language. 1. Subscribe to the Connector and grab your ScreenshotOne Access Key. 2. Add the key to your AI client configuration. 3. Ask your agent to capture a site or generate a PDF. ## Frequently Asked Questions **Can ScreenshotOne capture my whole website?** Yes, it can take full-page screenshots that capture the entire height of a site, not just what fits on your screen. **Can I turn a website into a PDF?** Yes, you can ask your agent to generate a PDF from any URL for easy sharing or offline viewing. **Does ScreenshotOne work for mobile views?** It can take screenshots at specific viewport sizes, so you can see how a site looks on a phone or tablet. **How do I get the metadata?** The Connector can pull the title and page size of a site without having to render the whole page first. **Can I target a specific button for a screenshot?** Yes, you can use it to capture a specific CSS element if you only need to see one part of a page. **Is this good for QA testing?** It's great for visual regression testing where you need to see if a layout changed between different versions. **How do I find my ScreenshotOne Access Key?** Log in to your [**ScreenshotOne dashboard**](https://screenshotone.com/app/settings), and you will find your Access Key under the 'API Keys' section. Copy and paste it below. **Can the agent capture elements by ID or Class?** Yes. Use the `take_element_screenshot` tool providing a valid CSS selector (e.g., `#header` or `.product-card`). Your agent will return a screenshot of just that element. **Is PDF generation supported for all sites?** Yes. The `generate_pdf` tool works for any publicly accessible URL, converting the website content into a high-quality PDF document instantly.