Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Aicon search for home icons in heroicons"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server + API for intelligent icon management with AI-powered generation and web-based authentication.
# 1. Install the MCP server
npm install -g aicon-mcp
# 2. Add to Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"aicon": {
"command": "aicon",
"args": []
}
}
}
# 3. Authenticate in Claude Desktop
# Use: login({action: "login"}) to start web authenticationSee DEPLOY.md for complete deployment instructions.
Related MCP server: Iconify MCP Server
🔍 Search Icons: Find from 275,000+ existing icons (Material, Heroicons, Lucide, etc.)
🎨 Generate Icons: Create custom icons using AI (powered by Runware.ai)
📥 Download Icons: Save as SVG or PNG with background removal
🔐 Web Authentication: Claude Code-style login flow with subscription plans
📊 Usage Tracking: Monitor API usage and rate limits
🔑 Secure: API key authentication with permission controls
Run login({action: "login"}) in Claude Desktop
Browser opens automatically for authentication
Login/register with credentials
Select subscription plan (Free/Pro/Enterprise)
API key generated and saved automatically
All icon tools now available!
🆓 FREE: 100 searches/month, SVG downloads
🚀 PRO: Unlimited searches + AI generation ($9/month)
🏢 ENTERPRISE: Everything unlimited + API access ($29/month)
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ MCP Server │───▶│ Backend API │───▶│ External APIs │
│ (Local) │ │ (Vercel) │ │ Iconify+Runware │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Claude Desktop │ │ Supabase DB │ │ Generated SVGs │
│ (AI Client) │ │ (Usage & Keys) │ │ (./Aicon/) │
└─────────────────┘ └─────────────────┘ └─────────────────┘/src/)Tools: 6 MCP tools including web authentication
Config: Multi-level configuration (env, user, project)
Storage: Local file management for downloaded icons
Client: HTTP client with request tracking
Endpoints: REST API for icon search, generation, usage
Auth: Production API key system with permissions
Database: Supabase integration for usage tracking
Processing: Image manipulation (Sharp, Potrace)
npm install
npm run dev # Development mode
npm run build # Build TypeScript
npm run typecheck # Type checking// Start web authentication in Claude Desktop
login({action: "login"})
// Check authentication status
login({action: "status"})
// View subscription plans
login({action: "plans"})// Search icons after authentication
search_icons({
query: "home",
library: "heroicons",
style: "outline"
})// Generate AI icons (Pro/Enterprise plans)
generate_icons({
subject: "rocket ship",
context: "space app",
style: "filled",
colors: "blue gradient"
})// Download icons in various formats
fetch_icons({
id: "heroicons:home",
type: "iconify",
format: "svg"
})✅ 275,000+ Icons from 200+ open source icon libraries
✅ AI Generation with background removal
✅ Web Authentication Claude Code-style login flow
✅ Subscription Plans Free/Pro/Enterprise tiers
✅ Format Support (SVG, PNG)
✅ Rate Limiting with usage tracking
✅ Production Ready with comprehensive tests
✅ Claude Integration via MCP protocol
MIT License - see LICENSE file for details.
Authenticate with your Icon MCP account through the web interface to access premium features.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Action to perform | |
| apiKey | No | API key (if you already have one) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden of behavioral disclosure. It reveals that authentication happens 'through the web interface', which hints at a browser flow, but it does not explain side effects (e.g., session creation), expected user interaction, return values, or the fact that the tool also performs status/plans/logout operations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler words or redundant restatement of the tool name. It is efficient but arguably too terse, sacrificing important scope information for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the multi-action enum, two parameters, no output schema, and no annotations, the description is inadequate. It does not mention the 'action' enum values, the web-interface interaction model, or any authentication prerequisites, leaving an agent under-informed about the full contract of the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-level information, and the schema's own parameter descriptions are minimal ('Action to perform', 'API key (if you already have one)'), but that is sufficient for a baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a verb ('Authenticate') and resource ('Icon MCP account'), but it is incomplete: the input schema's 'action' enum includes 'status', 'plans', and 'logout', none of which are acknowledged. This narrow framing makes the tool's actual scope misleading.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to use this tool versus alternatives, and no sibling tools are listed. The phrase 'to access premium features' implies a prerequisite for using premium features, but there is no explicit when/how/why guidance or any exclusion of cases where this tool should not be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.4.0loginScored across 1 tool
With only a single tool, there is no possibility of confusion between tools. The purpose of 'login' is clear and distinct within its narrow scope.
The single tool name 'login' is a clear, conventional verb that is easy to understand. There are no other tools to create inconsistencies or mixed naming conventions.
A single tool is too few for a server that promises 'premium features' and implies an underlying application surface. The server appears to offer authentication only, leaving core functionality unexposed.
The tool surface is severely incomplete. Only authentication is available; there are no tools to perform any actual premium functions, data operations, or other workflows that the login is meant to unlock.
Icons for agentic development: search & fetch 366,000+ open-source icons as SVG/PNG. No API key.
Multilingual semantic SVG icon search with previews for AI coding agents. 20,000+ icons.
320K+ open-source SVG icons: 12 tools, anonymous metadata search; SVG, exports, collections via Pro.
AI-agent image generation: cohesive sets & illustrations. Resize a set or export icons, free.
