Public assessment

Hugeicons MCP Server (@hugeicons/mcp-server, Smithery verified)

hugeicons-mcp-server · v0.1.0 · scanned Aug 3, 2026

What changed in the harness

Selection accuracy 98→100, token cost up 13%, unconfirmed writes 100%→100%.

Category breakdown

Where the score comes from.

Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.

01Safety

30.0 / 30

30.0 out of 30

02Legibility

26.4 / 30

26.4 out of 30

03Economics

20.0 / 20

20.0 out of 20

04Discoverability

12.0 / 20

12.0 out of 20

Highest-impact fix

Estimated gain +8 points

Make target tools discoverable on the first call

Clarify tool names, decision boundaries, and required argument schemas so an agent can choose and construct the target call without exploratory steps.

Description evidence

Defects and rewrites.

5 defects found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.

Tool	Defect types	Suggested rewrite
`list_icons`	no_return_description	Returns the full catalog of Hugeicons as a list of every available icon name, enabling discovery of the complete icon set before searching.
`search_icons`	name_restates_behavior no_return_description	Returns a list of icons matching the query, finding them by name or tags. Use commas to search multiple terms at once (e.g., 'home, notification, settings') and get icons matching any of them.
`get_platform_usage`	name_restates_behavior no_return_description	Returns the integration instructions (installation and usage guidance) for Hugeicons on a given platform. Specify the platform (react, vue, angular, svelte, react-native, flutter, or html) to get setup steps for that framework.
`get_icon_glyphs`	name_restates_behavior no_return_description	Returns every unicode glyph (character code) for a named icon across all available styles. Provide the icon name (e.g., 'home-01') to get the mapping of each style to its glyph.
`get_icon_glyph_by_style`	name_restates_behavior no_return_description	Returns the unicode glyph (character code) for an icon rendered in a specific style. Provide the icon name (e.g., 'home-01') and one of the supported styles (e.g., 'stroke-rounded') to get that style's character.

Selection evidence

Confusable tool pairs.

4 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.

Tool A	Tool B	Confidence	Why they collide
`get_icon_glyphs`	`get_icon_glyph_by_style`	high	Identical prefixes and both return unicode glyphs for a specific icon; a task like 'get the glyph for home-01' without specifying a style could select either, since one returns all styles and the other a single style.
`list_icons`	`search_icons`	medium	A task like 'find me icons' or 'show me icons for notifications' is ambiguous: the agent could list all icons or call the search tool; only explicit language like 'search for' or 'list all' disambiguates.
`search_icons`	`get_icon_glyphs`	low	A query like 'get me the home icon' could map to search_icons (name/tag search) or get_icon_glyphs (needs the icon name); the word 'glyph' or 'unicode' usually disambiguates, but generic phrasing creates mild overlap.
`search_icons`	`get_icon_glyph_by_style`	low	A task like 'find the home icon in solid style' could be interpreted as searching for the icon versus fetching its glyph for a specific style; the style keyword nudges toward get_icon_glyph_by_style, but 'find/get the icon' language is ambiguous.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard