Skip to main content
Glama
ethbak

Icon Composer MCP

by ethbak
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

export_preview

Render an .icon bundle preview as PNG with Liquid Glass effects, customizable background and zoom. Falls back to flat composite when Icon Composer is not available.

Instructions

Render a preview of an .icon bundle. Uses Apple's ictool for Liquid Glass rendering by default (falls back to flat composite if Icon Composer is not installed). Supports canvas backgrounds and zoom.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
flatNoForce flat composite rendering (skip ictool/Liquid Glass)
sizeNoOutput size in pixels
zoomNoZoom level — icon size relative to canvas (1.0 = full canvas, 0.5 = half size)
canvas_bgNoSimple preset canvas background
appearanceNoAppearance mode to preview (omit for default/light)
bundle_pathYesPath to .icon bundle
output_pathYesOutput path for the PNG file
apple_presetNoApple Icon Composer preset background (overrides canvas_bg)
return_imageNoReturn the rendered image inline as base64 (default true)
canvas_bg_colorNoCustom hex color for canvas background
canvas_bg_imageNoPath to custom background image

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.0
    • addedInput schema / properties / return_image
      Added value: +{
+  "default": true,
+  "description": "Return the rendered image inline as base64 (default true)",
+  "type": "boolean"
+}
  2. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description fully discloses key behaviors: default ictool usage, fallback to flat composite, and support for canvas backgrounds and zoom. It does not cover auth or destructive aspects, but as a preview tool, these are less critical.

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

Conciseness5/5

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

Two sentences, no wasted words. Front-loaded with the core purpose and followed by key technical details. Ideal conciseness for an AI agent.

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?

Despite 11 parameters and no output schema, the description covers essential behavior, fallback, and output options. It could include more on typical use cases or parameter interactions, but overall adequate.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description adds context on default rendering and fallback but does not elaborate on individual parameters beyond what the schema already provides.

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?

The description clearly states the tool renders a preview of .icon bundles, specifying the default rendering tool (ictool) and fallback. It distinguishes from sibling tools like export_marketing and render_liquid_glass by focusing on preview output.

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?

The description explains default behavior and fallback, and mentions support for backgrounds and zoom. However, it does not explicitly compare with alternatives like render_liquid_glass or export_marketing, leaving some ambiguity about when to choose each.

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

Deploy Server

Other Tools