What it does
The server renders web pages in a Chromium browser and returns either an image or a PDF. The capture_screenshot tool takes a URL, an optional viewport width and height (default 1280 x 720 px), a fullPage option for scrollable pages, and an output format of PNG, JPEG or WebP (default PNG). The webpage_to_pdf tool converts a live page to a PDF with a selectable paper format (default A4). Both tools are available over GET and POST.
The publisher positions these tools for visual QA testing, page thumbnails, archiving web pages, checking responsive design and visual regression testing in automated pipelines. The PDF tool suits printable articles, saving receipts or invoices from URLs, and offline documentation snapshots. The readme points users to other tools for text extraction and for PDFs generated from HTML or Markdown.
It can be added to an MCP client configuration such as Claude Desktop or Cursor, or called directly over HTTP. Each call is paid through x402 in USDC on Base L2, at $0.015 per screenshot and $0.02 per PDF, with no API key or signup. An x402-aware client handles the payment cycle. The readme lists Coinbase CDP as the primary facilitator and PayAI as a fallback, and notes access through ATXP. The project is released under the MIT license.
Limitations and requirements
Each call is paid in USDC on Base L2 through the x402 protocol, so the client must support x402 payments.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Screenshot & PDF Capture API
Capture screenshots (PNG/JPEG/WebP) and generate PDFs from any URL. x402 payments.
v1.2.0As shown on registry.modelcontextprotocol.io when we last read it