Call page.ingest_bundle
Bring in a site the member already built somewhere else — 'import my existing site', 'I have a zip of my site', 'pull in the one I built in Webflow'. It takes a public https:// link to a .zip — either a finished build or a project we compile. Give it a site_id to replace an existing site, or leave it out to create a new one. It does NOT publish: say the site was imported, not that it is live. A private, local or metadata address is refused, and so is http:// — relay that refusal rather than retrying. If findings come back, they are advisory notes about search/AI discovery, never a failure of the import. The import_report says what we detected, what came across, what we changed to host it and what could not be brought over: relay those lists, never summarise them away. While import_report.status is "compiling" the site is still being built, so page_count is not yet the answer. Not for building a new site from scratch — that is page.create.
Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.
Request
- Base URL: https://app.goosybear.ai
- URL: https://app.goosybear.ai/api/v1/tools/page.ingest_bundle
- Auth: HTTP bearer
Headers
Your own id for this request, echoed back and recorded on the audit trail. 1–128 characters from A–Z a–z 0–9 . _ : -, starting with a letter or digit; anything else is replaced by a generated id.
Request body
Response
The call was admitted and dispatched. ok says whether the tool succeeded — a refusal the tool itself produced is still a 200, exactly as it is a successful JSON-RPC result over MCP.
Changes
No recorded changes to this operation across all 6 revisions of this API.