What it does
The server takes a URL or HTML and returns either a screenshot in PNG, JPEG or WebP format, or a text version of the content in clean Markdown or plain text, formatted for use with LLMs.
It suits tasks where an AI assistant needs a visual capture of a web page or needs a page's content in a readable text form.
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
com.apiscreenshot/screenshot
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
v1.1.0As shown on registry.modelcontextprotocol.io when we last read it