What does generateImage do?

Generate an image and save it as a real asset inside a Studio app (Private by default). It is one of the tools The Cloud MCP server gives every connected AI.

How do I use generateImage from Claude or ChatGPT?

Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "make an image of X", and it calls generateImage.

Is generateImage safe to let an AI call?

generateImage changes your workspace. What an AI creates is Private until you share it. It reaches a system outside The Cloud on your behalf.

Media & Video

`generateImage`

Generate Image

Generate an image and save it as a real asset inside a Studio app (Private by default).

writeexternal

Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "make an image of X", and it calls generateImage.

Example call

The MCP tools/call params, with the required arguments only.

{
  "arguments": {},
  "name": "generateImage"
}

Arguments

appIdstringoptionalOptional Studio app to save into; a new app is made if absent
engineIdstringoptionalOptional engine: nano-banana (Google Gemini) or higgsfield-soul (premium: needs the user's own key). Both support editing. Defaults to the user's preferred engine, else Higgsfield then Nano Banana.
namestringoptionalName for the new app when appId is absent
presetIdstringoptionalA saved photo preset (a slug from listGenerationPresets, e.g. "product-photography"). Pass `subject` with it and leave `prompt` off: the preset supplies the exact calibrated sentence, its engine and its background. Do NOT retype the…
promptstringoptionalWhat to generate. Required unless you pass presetId.
subjectstringoptionalThe one plain subject the preset is about, e.g. "a vanilla cupcake with white frosting". Required with presetId.
allowFallbackbooleanoptionalIf the chosen engine is unavailable, capped, or fails, produce on the next connected engine and note the substitution
aspectRatiostringoptionalAspect ratio like "1:1" or "16:9"
backgroundstringoptionalThe background colour you asked for, as a word ("cream", "white", "beige", "mustard") or a hex ("#FFFDF0"). The server samples the finished image's border, reruns ONCE by itself if the mean is far from what you asked for, and reports the…
heightnumberoptionalOutput height in px (e.g. 1024)
internalAssetbooleanoptionalADMIN ONLY. Generate a Teka internal asset on Teka's platform premium key instead of your own (HD Digi icons, waiting-room landscapes, brand marks). Refused for non-admins; ignore for normal generations.
transparentBackgroundbooleanoptionalRender on a transparent background (icons/cutouts)
variantsnumberoptionalHow many variations to produce (1-4)
widthnumberoptionalOutput width in px (pair with height, e.g. 1024)

Returns

Generation runs in the background (it can take a while and never blocks past the tool timeout): returns a jobId + app link immediately.

Ask for it

The Cloud routes these requests to this verb.

make an image of X
generate a photo of Y
shoot this product

Pair it with

The verbs that finish the job.

Questions

What does generateImage do?
Generate an image and save it as a real asset inside a Studio app (Private by default). It is one of the tools The Cloud MCP server gives every connected AI.
How do I use generateImage from Claude or ChatGPT?
Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "make an image of X", and it calls generateImage.
Is generateImage safe to let an AI call?
generateImage changes your workspace. What an AI creates is Private until you share it. It reaches a system outside The Cloud on your behalf.

Connect

One endpoint gives your AI this tool and every other one: connect Claude, ChatGPT, Cursor or Gemini, read what The Cloud is, or see pricing.