clone
Copy an existing web page into native sections, or extract its text and images as a blueprint to rebuild or migrate storefront content.
Instructions
Copy an existing web page as native sections (clone_page), or read a page's text/images as a blueprint (ingest_*). Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).
clone_page: Clone a web page into NATIVE sections (text/image/button/form/video/container rows — no embed, no custom code).
get_clone_script: Get the capture script for clone_page: run it inside the source page with YOUR browser tool when clone_page can't open the page itself (remote server, no local Chrome, a page be…
ingest_url: Fetch a public URL and parse it into a structural blueprint (see ingest_html).
ingest_html: For a faithful copy of a live page use clone_page (native sections from the rendered layout).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"action": "<action>"
},
"name": "clone"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Page to clone (public URL) [clone_page, ingest_url] | |
| help | No | Return the action's full documentation and argument schema instead of running it | |
| html | No | Raw HTML to analyse [ingest_html] | |
| width | No | Capture width in px (default 1440) [clone_page] | |
| action | Yes | Which operation to run | |
| snapshot | No | Result of the get_clone_script script (object or JSON string), instead of url [clone_page] | |
| skip_chrome | No | Leave out the source's header/footer/nav (use the site's global ones). [clone_page] | |
| rehost_images | No | Upload images (and svg icons as PNG) to the WebCake CDN (default false) [clone_page] |