Generate AI QR art
generate_ai_artPaint a QR code into AI artwork from a description: the art painted into the code's modules (mode "code"), a picture painted from the description with the code painted into its middle, so the picture runs through the code ("scene"), or the same with your own photo ("photo"). QRdx checks that the image scans to the content and strengthens the code just enough when it doesn't. Encodes text, or a dynamic code's short link by its id (code) so the destination stays editable and scans are counted. Needs a QRdx API key with full access on this MCP connection (Authorization: Bearer qrdx_…). Each call uses one image from the workspace's paid monthly AI art allowance (3 on Free, 30 on Pro, 150 on Business, shared by the team), refunded when no scannable image comes back. Code mode takes 15-45 seconds, photo mode about 25-45 and scene mode about 40-55 (it makes the picture first); a scene that runs out of time is refunded with AI_ART_TIMEOUT, so retry it or use code mode. Returns a 1024 px PNG, the seed, how the code was made to scan and the images left this month.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "generate_ai_art"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | The id of one of the workspace's dynamic codes: the art encodes its short link, so its destination stays editable and scans are counted. Send this or text, not both. | |
| mode | No | How the code sits in the art: "code" (default; the art painted into the code's modules), "scene" (a picture is painted from the description first, then the code is painted into its middle, so the picture runs through the code; about 40-55 seconds) or "photo" (the same with your photo as the picture; needs photo; about 25-45 seconds). | |
| seed | No | A seed, to make a similar image again | |
| text | No | What the code encodes: a link or text, up to 300 characters. Send this or code, not both. | |
| photo | No | Photo mode: your picture as a PNG or JPEG data: URL (data:image/jpeg;base64,…), cropped square and downsized to about 1024 px (at most 1 MB). It goes to the model and is discarded. | |
| style | No | A quick look, added to the prompt: watercolor (Watercolor), oil-painting (Oil painting), anime (Anime), cartoon (Cartoon), pixel-art (Pixel art), pop-art (Pop art), charcoal (Charcoal), ink (Ink), cyberpunk (Cyberpunk), fantasy (Fantasy), photographic (Photographic), low-poly (Low poly), papercut (Papercut) | |
| prompt | No | The artwork to paint, in plain words (up to 400 characters), such as "a koi pond at dusk". Leave it out and QRdx writes one for the mode, look and photo; the result then says what it wrote. | |
| reference | No | A reference image for the look, as a PNG or JPEG data: URL, downsized to about 512 px. It goes to the model and is discarded. | |
| creativity | No | 0-100 (default 45): low follows the prompt literally, high interprets it freely | |
| visibility | No | QR visibility, 0-100 (default 50): higher shows the code more clearly, lower favors the picture | |
| negativePrompt | No | What to keep out of the picture |