Skip to main content
Glama

Generate AI QR art

generate_ai_art

Paint 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

NameRequiredDescriptionDefault
codeNoThe 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.
modeNoHow 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).
seedNoA seed, to make a similar image again
textNoWhat the code encodes: a link or text, up to 300 characters. Send this or code, not both.
photoNoPhoto 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.
styleNoA 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)
promptNoThe 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.
referenceNoA 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.
creativityNo0-100 (default 45): low follows the prompt literally, high interprets it freely
visibilityNoQR visibility, 0-100 (default 50): higher shows the code more clearly, lower favors the picture
negativePromptNoWhat to keep out of the picture

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes far beyond the annotations: it discloses the required Bearer API key with full access, the paid monthly allowance and its per-tier size with team sharing, the refund policy when no scannable image is returned, per-mode latency, and the specific AI_ART_TIMEOUT failure and recovery. It also states the return payload (1024 px PNG, seed, scan-fix notes, remaining images), which annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and then ordered by mode, encoding, auth, quota, timing, and return — a sensible progression with no filler sentences. It is a dense block rather than scannable lines, and the per-mode durations appear in both the description and the schema, which is mild duplication.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with no output schema, the definition covers what is needed to invoke it correctly: input exclusivity, mode behavior and cost in time, auth prerequisites, quota accounting, and the shape of the result. Nothing an agent would need before calling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3; the description earns a nudge by explaining the intent behind the mutually exclusive code/text pair (destination stays editable, scans counted) and by tying photo/scene to their timing and photo requirement. Most field-level detail, however, duplicates what the schema already documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: "Paint a QR code into AI artwork from a description," then immediately enumerates the three output shapes (code/scene/photo) so the agent knows exactly what artifact comes back. It is clearly distinct from a plain QR generator because the deliverable is art with an embedded, scannability-checked code.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong in-tool routing: mode "code" when you want the art inside the modules, "scene" when the picture should run through the code, "photo" when supplying your own image, plus a fallback rule (retry on AI_ART_TIMEOUT or drop to code mode). What it omits is comparison against siblings like generate_qr_code or design_qr, so an agent must infer that a non-art QR belongs elsewhere.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.