ModelsAtlas
Explore
Atlas / MCP servers / better-auth / Better Icons

Better IconsSAFE

mcp/better-auth/better-icons
MCP server by better-auth · Audited 2026-09-25
⚑ Report / re-scanSource ↗

Skill and MCP server for searching and retrieving icons

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
11 9r · 1w · 1d
Transport
stdio
License
MIT
Stars
1,289
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Search and retrieve 200,000+ icons from 150+ icon collections. Works as an MCP server for AI agents or CLI tool.

Quick Start

Add Skills

Enable the better-icons CLI features in your agent environment (matches all examples below):

npx skills add better-auth/better-icons

Direct CLI Installation

Alternatively, install the CLI globally for direct non-agent use:

# Using npm
npm install -g better-icons

# Using Bun (faster)
bun add -g better-icons

MCP Server (AI Agents)

Configure the MCP server to enable icon tools in your AI coding agents.

npx better-icons setup

This interactively configures the MCP server for:

  • Cursor
  • Claude Code
  • OpenCode
  • Windsurf
  • VS Code (Copilot)
  • Google Antigravity

Or configure manually.

CLI (Direct Usage)

Use the CLI to search and retrieve icons directly from your terminal.

# 1. Search for icons (finds icons across 150+ collections)
npx better-icons search arrow --limit 10
npx better-icons search home --prefix lucide

# 2. Get icon SVG (outputs raw code or saves to file)
npx better-icons get lucide:home > icon.svg
npx better-icons get mdi:account --color '#333' --size 24

# 3. JSON output for scripting
npx better-icons search settings --json | jq '.icons[:5]'
npx better-icons get heroicons:check --json

Why?

Icons are a common pain point in AI-assisted coding. Models often struggle to know which icons are available, generate correct SVG code, maintain consistent styles, and organize icons properly. Inline SVGs also consume unnecessary tokens.

Features

  • 200,000+ Icons - Search across 150+ icon collections (Lucide, Heroicons, Material Design, etc.)
  • Auto-Learning - Remembers which icon collections you use and prioritizes them in future searches
  • Project Sync - Icons are written directly to your icons file (.tsx, .ts, .js) instead of pasting SVG into chat (saves
Read from source at commit 763101a9457eOBSERVED · 2026-09-25
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add better-icons -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "better-icons": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (11)

9 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
clear_icon_preferencesdestructive
find_similar_iconsread
get_iconread
get_icon_preferencesread
get_iconsread
get_recent_iconsread
list_collectionsread
recommend_iconsread
scan_project_iconsread
search_iconsread
sync_iconwrite
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
clear_icon_preferences
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@clack/prompts, @modelcontextprotocol/sdk, chalk, commander, @types/bun, bumpp
Why it matters. 6 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-09-25 · audit v0.4.1 · source sha 763101a9457efull audit observations/trust-audit/mcp-server/better-auth__better-icons.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-09-25763101a9457eSAFEB89first audit
06

Questions

What is the Better Icons MCP server?

Skill and MCP server for searching and retrieving icons

What tools does Better Icons expose?

11 in total: 9 read-only, 1 that write, and 1 that can delete or overwrite (clear_icon_preferences). Every one is listed on this page with its risk.

Is Better Icons safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Better Icons need?

No credential environment variables were found in its source, so it appears to need none.

How does Better Icons run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as better-icons at 1.0.5.

How current is this page?

The grade is for one exact copy of the source (763101a9457e), read on 2026-09-25. The repository is watched and re-audited when it changes.

Advertisement