Call browser.read
Drive a real browser to a page on a site this workspace has APPROVED for browsing and pull named fields off it — 'use the browser to pull the prices off our supplier's page', 'open our approved site in the browser and read the plan table'. Open a web page this workspace has approved for browsing and READ it — pull named fields off it, or answer a question about what is on it. This one is for the approved sites that need a real browser. It only reaches sites the workspace has added on Settings → Assistant → Browser; anything else is refused with the domain to add. It reads and never types, clicks through a form, signs in, or changes anything on the page. Not for an ordinary link someone pastes, or any site to just read — that is web.read. Over the API it answers in two calls: without confirmation_id it proposes — says what would happen, returns a confirmation_id and changes, spends and sends nothing; the same arguments again with that confirmation_id, on a member's own API key, do it.
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/browser.read
- 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 4 revisions of this API.