Favicon & App Icons

Generate a favicon and app-icon set

generate_iconset

Use this when someone asks to create, replace, or install favicons, website icons, Apple touch icons, PWA icons, or app icons. Generates favicon.ico, PNG sizes, Apple/Android icons, theme-aware icons, manifests, environment variants, downloadable URLs, and an install snippet from one image, URL, or Iconify name. This creates hosted output files but does not edit the caller's project. Call search_icons first if you need a source.

Input Schema

Name	Required	Description
`apiKey`	No	ft_… key from a previous call for a higher rate limit.
`source`	Yes	Iconify name (prefix:name), an http(s) image URL, or a base64/data-URL image.
`customSizes`	No	Extra exact PNG sizes a platform demands, e.g. [255] for Adobe's 255×255 or ['300x150']. Each becomes icon-WxH.png (16–4096px, max 12). Production only; not in the head snippet or manifest.
`docsVariant`	No	Also emit the outlined docs-* tab-icon set + docs-manifest.json.
`variantType`	No
`primaryColor`	No	Hex color, e.g. #61dafb.
`backgroundColor`	No	none \| white \| black \| #rrggbb
`backgroundShape`	No
`docsBorderColor`	No	Docs ring colour: accent \| contrast \| white \| #rrggbb.
`excludeFromGraph`	No	When true, skip recording this generation to analytics.
`includeDevVariations`	No
`includeThemeAwareFavicon`	No

Output Schema

Name	Required	Description	Default
`note`	No
`files`	Yes
`apiKey`	No
`install`	Yes
`manifest`	Yes
`circleFit`	No
`headSnippet`	Yes
`safariPinnedTab`	No
`excludedFromGraph`	Yes
`appliedBackgroundShape`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 20, 2026

addedInput schema / properties / customSizes

Added value: +{
+  "description": "Extra exact PNG sizes a platform demands, e.g. [255] for Adobe's 255×255 or ['300x150']. Each becomes icon-WxH.png (16–4096px, max 12). Production only; not in the head snippet or manifest.",
+  "items": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "string"
+      },
+      {
+        "additionalProperties": false,
+        "properties": {
+          "height": {
+            "type": "integer"
+          },
+          "width": {
+            "type": "integer"
+          }
+        },
+        "required": [
+          "width",
+          "height"
+        ],
+        "type": "object"
+      }
+    ]
+  },
+  "type": "array"
+}

Changed5 schema fields changedOct 8, 2026

addedInput schema / properties / backgroundColor / anyOf

Added value: +[
+  {
+    "enum": [
+      "none",
+      "white",
+      "black"
+    ],
+    "type": "string"
+  },
+  {
+    "pattern": "^#?([0-9a-fA-F]{3}|[0-9a-fA-F]{6})$",
+    "type": "string"
+  }
+]

addedInput schema / properties / backgroundColor / description
```
Added value: +"none | white | black | #rrggbb"
```

removedInput schema / properties / backgroundColor / enum

Removed value: -[
-  "none",
-  "white",
-  "black"
-]

removedInput schema / properties / backgroundColor / type
```
Removed value: -"string"
```

addedOutput schema / properties / safariPinnedTab

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "included": {
+      "type": "boolean"
+    },
+    "reason": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "included"
+  ],
+  "type": "object"
+}

First observedOct 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: output is hosted files rather than project edits, plus the install snippet and downloadable URLs. It stops short of stating persistence/expiry of hosted output or rate-limit behavior.

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?

Three sentences, front-loaded with the trigger condition, then the output inventory, then the scope caveat and alternative-tool pointer. No filler and nothing repeated from the schema.

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?

An output schema exists, so return values need no explanation, and the description nonetheless summarizes the deliverable set. Combined with annotations covering safety and world-openness, an agent has everything needed to select and call it.

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?

With 12 parameters and 67% schema description coverage, the schema carries most parameter meaning, and the description only restates the source types ('image, URL, or Iconify name') already documented in the schema. It adds no guidance on customSizes, variantType, backgroundShape, or theme-aware toggles.

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?

States a concrete verb+resource ('Generates favicon.ico, PNG sizes, Apple/Android icons, theme-aware icons, manifests...') and explicitly enumerates the artifact set, which no sibling produces. It also differentiates itself from search_icons by routing source discovery there.

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

Usage Guidelines5/5

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

Gives explicit trigger phrasing ('when someone asks to create, replace, or install favicons...') and names the alternative tool plus the condition for using it ('Call search_icons first if you need a source'). It also carves out scope: it does not edit the caller's project.

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

All Favicon & App Icons tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?