MCP Tools Reference

The MCP server exposes two tools. Both render in real Chrome, both cost 1 credit per successful image, and both return a full-resolution CDN URL plus a downscaled preview image so the model can review the result.

The parameters mirror the REST API parameters, with three differences: there is no webhook_url (MCP calls are synchronous), there is no scale_to_fit, and the default viewport is 1920x1080 rather than the REST API’s 1440x900.

generate-image-from-html

Renders HTML and CSS to a PNG or PDF. Best for content the model designs itself: social cards, OG images, invoices, certificates, receipts, charts and more.

Parameter	Type	Required	Description
html	string	Yes	Complete, self-contained HTML to render. Put CSS in an inline <style> block.
css	string	No	Extra CSS injected into the page.
width	integer	No	Viewport width in pixels (1-5000). Defaults to 1920.
height	integer	No	Viewport height in pixels (1-5000). Defaults to 1080.
fullpage	boolean	No	Capture the full scrollable height instead of the viewport.
dpi	integer	No	Device pixel ratio (1-4) for higher-resolution output.
ms_delay	integer	No	Milliseconds to wait before capture, 1-5000 (e.g. to let fonts or animation settle).
wait_for_selector	string	No	Wait until this CSS selector appears before capturing.
format	string	No	png (default) or pdf. With pdf, width, height, dpi and fullpage are ignored. See the format parameter.

screenshot-url

Captures a screenshot of a live, publicly accessible web page.

Parameter	Type	Required	Description
url	string	Yes	The fully-qualified URL to capture (https://...).
css	string	No	CSS injected into the page before capture (e.g. to hide cookie banners).
width	integer	No	Viewport width in pixels (1-5000). Defaults to 1920.
height	integer	No	Viewport height in pixels (1-5000). Defaults to 1080.
fullpage	boolean	No	Capture the full scrollable height instead of the viewport.
selector	string	No	Capture only the element matching this CSS selector (first match wins). Maximum 255 characters.
dpi	integer	No	Device pixel ratio (1-4).
ms_delay	integer	No	Milliseconds to wait before capture, 1-5000.
wait_for_selector	string	No	Wait until this CSS selector appears before capturing.
format	string	No	png (default) or pdf. With pdf, width, height, dpi, fullpage and selector are ignored. See the format parameter.

Output

On success, a tool returns two things to the model:

1. A text part with the full-resolution image URL on the i.html2img.com CDN and your remaining credit balance.
2. An image part - a downscaled preview of the render, so the model can see what it produced and iterate. PDFs return the URL only, plus a line noting the file is an A4 vector PDF with selectable text; there is no inline preview for PDFs.

The full-resolution file always lives at the returned URL. The inline preview is intentionally small so it fits inside the message-size limits of MCP clients.

Credits and errors

• Each successful image costs 1 credit, exactly like the REST API.
• If you are out of credits, the tool returns a clear message instead of an image, and no credit is spent. Top up on the pricing page.
• Render failures (timeouts, unreachable pages, invalid input) come back as readable tool errors so the assistant can adjust and try again.

Images in your HTML

See also

• Install and setup for your AI client.
• Parameters reference for the shared rendering options in depth.