The HTML/CSS to Image MCP server lets AI assistants create production-ready images, website screenshots, and PDFs through natural-language instructions.
Use it to:
- Render HTML and CSS into PNG, JPG, WebP, or PDF
- Capture screenshots of public URLs
- Generate images from reusable templates and variables
- Create batches of multiple image variations
- Create, update, list, and version image templates
- Configure viewport size, device scale, selectors, render delays, and other rendering options
How to use
- 1Add it in ChatGPT
Open HTML/CSS to Image API in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.
- 2Use it in a chat
Type @ in the composer and pick HTML/CSS to Image API, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.
Things to ask
- “Create a polished 1200×630 social image for a product launch with bold type, a modern gradient, and a clear call to action.”
- “Create a batch of my website screenshots across desktop, tablet, and mobile sizes, time zones, and light and dark modes.”
- “Create a reusable event image template with fields for the name, date, location, and call to action, then render an example.”
Disconnect
- 1Disconnect it in ChatGPT
Open Settings, then Apps or Plugins (the label depends on your rollout), select HTML/CSS to Image API and choose Disconnect. ChatGPT stops acting through your account; past conversations aren't deleted.