Call images.generate
Generate images onto a board in this workspace. This SPENDS CREDITS, so it takes two calls: the first returns what would be made plus a confirmation id and charges nothing, and the second — carrying that id back — is what actually runs it. There is no way to run it in one call, by design.
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.
Authorizations
An API key minted at Settings › API & MCP. Send it as Authorization: Bearer <key>. A key carries its holder's own permissions, resolved on every call — revoking a membership closes the key's reach immediately. Keep it in an environment variable (GOOSY_API_KEY), never in a committed file.
Body
Which board the images land on — a board id in this workspace.
What to generate, in plain words.
1 - 2000How many images to make. Each one costs credits.
1 <= x <= 10The aspect ratio. Omit for the workspace default.
1:1, 3:4, 4:3, 9:16, 16:9 Leave this out on the first call: the answer will describe the run and hand you an id. Send that id back, unchanged, to actually run it.
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.
1Response
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.
- Option 1
- Option 2
The tool ran and answered.
confirmation_required — nothing ran and nothing was charged; dispatched — the run is under way.
confirmation_required, dispatched Present only while confirmation is required. Send it back on the second call.
Present only while confirmation is required — what will be made, in one sentence, for a person to approve.
How many images this run covers.
Present only once dispatched — the run to follow.
The slug of the workspace this call ran in.
Which workspace this call ran in, and how that was decided. Present on every workspace-scoped result.