brand_kit

Call brand_kit.read

'what's our one-liner?', 'which offer is running right now?', 'find the photo of Alex at the counter' — read this workspace's brand kit: who the brand is, what it offers, who it is for, how it sounds and looks, where it is, its video settings, and its pictures by label, kind and tag (never the files). Each fact says whether a member confirmed it or it is still a suggestion; a suggestion carries the fact_id and updated_at a member confirms on the brand page. A large kit comes back in part, with omitted naming the groups to read next by group. It changes nothing. Not for adding or correcting a fact — that is brand_kit.suggest.

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.

post/api/v1/tools/brand_kit.read

Request

  • Base URL: https://app.goosybear.ai
  • URL: https://app.goosybear.ai/api/v1/tools/brand_kit.read
  • Auth: HTTP bearer

Headers

x-request-idstring

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

group'identity' | 'offer' | 'audience' | 'verbal' | 'visual' | 'reach' | 'video'

Only this section of the kit. Omit for the whole kit; a long section comes back in part, and omitted names what to read next.

kindstring

Only this kind of fact — every row of one list, by the kind a section of sections names. Use it to read the whole of a list sections says was shortened (shown below its count).

cursorstring

The next page of the list read with kind: pass the next_cursor the last read returned, with the same kind. Omit it for the first page.

library_querystring

A word to find pictures by — a label, a kind or a tag ('book cover', 'person', 'product').

workspacestring

Which workspace to run in — its slug. Omit to use your default. With more than one reachable workspace and no default, the call is refused and the choices are listed.

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.

OR

Changes

No recorded changes to this operation across all 4 revisions of this API.