ScreenshotMCP

Captures complete webpage screenshots including content below the fold by rendering the full DOM and scrolling through the entire page height. Uses headless browser automation (likely Puppeteer or Playwright) to load pages, wait for dynamic content, and serialize the full rendered output as PNG/JPEG, handling variable page heights and responsive layouts automatically.

Captures screenshots of specific DOM elements identified by CSS selectors or XPath expressions. The tool renders the page, locates the target element, measures its bounding box, and extracts only that region from the rendered output, enabling focused visual inspection without capturing surrounding page content.

Captures screenshots at predefined device viewport sizes (mobile, tablet, desktop) by configuring the headless browser's viewport dimensions before rendering. Applies device-specific user agents and viewport metrics to simulate how pages render across different screen sizes, enabling responsive design validation without manual device testing.

Registers screenshot capture functions as standardized MCP tools with JSON schema definitions that describe input parameters, output types, and tool behavior. The schema enables Claude and other MCP clients to understand available screenshot operations, validate inputs, and parse responses without custom integration code.

Processes screenshot requests asynchronously through the MCP message queue, allowing multiple concurrent screenshot operations without blocking the main event loop. Uses Promise-based browser automation and async/await patterns to manage headless browser lifecycle, page navigation, and image rendering in parallel.

Implements intelligent waiting mechanisms that detect when dynamically-loaded content has finished rendering before capturing screenshots. Uses strategies like waiting for network idle, monitoring DOM mutations, polling for specific elements, or explicit wait conditions to ensure JavaScript-heavy pages are fully rendered before image capture.

Allows configuration of output image format (PNG, JPEG), compression quality, and rendering options through tool parameters. Enables callers to optimize for file size vs. visual fidelity based on use case, supporting both lossless PNG for precise visual comparison and lossy JPEG for bandwidth-efficient transmission.

Implements comprehensive error handling for screenshot failures including network errors, timeout conditions, rendering failures, and invalid inputs. Returns structured error responses with diagnostic information (error type, timeout details, page load status) that help agents understand why a screenshot failed and potentially retry with different parameters.