Skip to main content
Glama

AMNT SVG

by io.amnt
OverviewDiscussionsAdmin

svg_generate

AMNT SVG: describe a picture and get a clean, editable SVG (real shapes, not a bitmap). Pick a "model": amnt-auto (AMNT Auto) picks the best one per request ($0.01-$0.25, shown before it runs); without one it uses AMNT Draw 1.2: $0.05 standard, $0.15 HD, any shape. Takes 8-60 s.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNocutout = no overlapping shapes, for Figma and cutting machines.
modelNoThe AMNT model. Leave it out for AMNT Draw 1.2, the default. amnt-auto (AMNT Auto, $0.03): Picks the best AMNT model for each request. · amnt-svg-lite-1.1 (AMNT SVG Lite 1.1, $0.01): Simple icons, charts, patterns and flat backgrounds. Fastest and cheapest. · amnt-svg-1.1 (AMNT SVG 1.1, $0.03): Icons, logos, lettering, NFT bases and traits, as tiny clean SVG code. · amnt-svg-pro-1.1 (AMNT SVG Pro 1.1, $0.25): Characters, mascots and detailed art. The best NFT bases. · amnt-trace-1.2 (AMNT Draw 1.2, $0.05): Icons, logos, pixel art and illustrations with a few true colours. · amnt-vectorize-1.1 (AMNT Vectorize 1.1, $0.08): Turn your picture into a clean SVG. Logos and icons come back as tiny clean code. · amnt-animate-1.1 (AMNT Animate 1.1, $0.05): One prompt, a moving SVG. Every moving part is its own named group. Hand-drawn or flat.
styleNoflat, icon and logo trace cleanest.
aspectNo"auto", 1:1, 4:5, 3:4, 2:3, 9:16, 1:2, 5:4, 4:3, 3:2, 16:9, 2:1, or any W:H up to 3:1. Same price in every shape.
colorsNoCap the number of colours.
detailNolow = bold and simple, medium = clean (default), high = closest to the picture.
layersNoobjects = each thing (hat, face...) as its own named, movable group, drawn whole underneath. +$0.02.
promptYesWhat to draw.
formatsNoExtra files: png, pdf, eps, dxf (cutting machines), icons (favicon pack zip), small.
objectsNoName the objects to separate, if you know them.
paletteNoSnap every colour to these (brand colours).
qualityNohd keeps finer detail: $0.15 instead of $0.05.
backgroundNotransparent removes a plain backdrop with no white ring.
include_svgNoPut the SVG markup in the reply. Off by default: traces are large.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"The AMNT model. Leave it out for the classic drawn-then-traced SVG. amnt-auto (AMNT Auto, $0.03): Picks the best AMNT model for each request. · amnt-svg-lite-1.1 (AMNT SVG Lite 1.1, $0.01): Simple icons, charts, patterns and flat backgrounds. Fastest and cheapest. · amnt-svg-1.1 (AMNT SVG 1.1, $0.03): Icons, logos, lettering, NFT bases and traits, as tiny clean SVG code. · amnt-svg-pro-1.1 (AMNT SVG Pro 1.1, $0.25): Characters, mascots and detailed art. The best NFT bases. · amnt-trace-1.2 (AMNT Draw 1.2, $0.05): Drawn by AMNT Image, then traced clean: icons, logos, pixel art and illustrations with a few true colours. · amnt-vectorize-1.1 (AMNT Vectorize 1.1, $0.08): Turn your picture into SVG: logos and icons redrawn as clean code, the rest traced. · amnt-animate-1.1 (AMNT Animate 1.1, $0.05): One prompt, a moving SVG: the parts that should move are drawn apart, named and animated. Hand-drawn or flat."New value: +"The AMNT model. Leave it out for AMNT Draw 1.2, the default. amnt-auto (AMNT Auto, $0.03): Picks the best AMNT model for each request. · amnt-svg-lite-1.1 (AMNT SVG Lite 1.1, $0.01): Simple icons, charts, patterns and flat backgrounds. Fastest and cheapest. · amnt-svg-1.1 (AMNT SVG 1.1, $0.03): Icons, logos, lettering, NFT bases and traits, as tiny clean SVG code. · amnt-svg-pro-1.1 (AMNT SVG Pro 1.1, $0.25): Characters, mascots and detailed art. The best NFT bases. · amnt-trace-1.2 (AMNT Draw 1.2, $0.05): Icons, logos, pixel art and illustrations with a few true colours. · amnt-vectorize-1.1 (AMNT Vectorize 1.1, $0.08): Turn your picture into a clean SVG. Logos and icons come back as tiny clean code. · amnt-animate-1.1 (AMNT Animate 1.1, $0.05): One prompt, a moving SVG. Every moving part is its own named group. Hand-drawn or flat."
    • addedInput schema / properties / quality / description
      Added value: +"hd keeps finer detail: $0.15 instead of $0.05."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does well: it reveals latency (8-60 s), a price band ($0.01-$0.25) with a pre-run quote, the default model, and the output character (editable real shapes, not a bitmap). It omits auth/rate-limit constraints and failure behavior, which keeps it from a 5.

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?

Roughly three sentences, front-loaded with the core purpose before model/cost/timing detail, and every sentence carries information about cost, default, or latency. The pricing clause is slightly dense but not wasteful.

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

Completeness4/5

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

For a 14-parameter, no-annotation, no-output-schema tool, the description supplies the operational facts an agent most needs: what it produces, default behavior, cost, and duration. What comes back beyond 'a clean editable SVG' and error/retry behavior remains unstated, leaving a small gap.

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 the parameter baseline is 3, but the description adds cross-parameter meaning the schema does not: the cost range across models, the pre-execution price display, and the default-model fallback when 'model' is omitted. That is genuine added value over the enum descriptions.

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

Purpose4/5

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

States a specific verb and resource: 'describe a picture and get a clean, editable SVG (real shapes, not a bitmap)'. The text-to-SVG framing implicitly separates it from the image-to-SVG sibling svg_vectorize, but no sibling is named explicitly, so it falls short of full differentiation.

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

Usage Guidelines3/5

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

The description explains model selection behavior ('Pick a model: amnt-auto picks the best one per request...; without one it uses AMNT Draw 1.2') and gives cost/latency, which helps an agent decide how to call it. However it never states when to prefer this tool over svg_vectorize or svg_library_search, so usage is only implied.

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

All AMNT SVG toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources