mcpField
R
Remix Icon MCP

Remix Icon MCP

Local
github.com/FradSerMedia & Design95Updated today

About Remix Icon MCP

Remix Icon MCP is a lightweight MCP server that maps icon-related keywords to Remix Icon metadata using local FlexSearch indexing. It returns the top 5 matching icons per query, aimed at developers and AI assistants choosing icons.

Key features

  1. 01Accepts up to 20 comma-separated keywords
  2. 02Returns a fixed top five matching icons
  3. 03Local search using a FlexSearch v0.8 document index
  4. 04Layered architecture separating domain, application and infrastructure
  5. 05Runs as a command line tool via npx

Use cases

  1. 01Finding interface icons from keywords inside an AI assistant
  2. 02Selecting one Remix Icon for a design or coding task

MCP support

The server exposes a search_icons tool over stdio using JSON-RPC 2.0, returning ranked candidates, matched tokens and guidance for choosing one icon.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"remix-icon": {
"command": "npx",
"args": [
"-y",
"remixicon-mcp"
]
}
}
}
Run commandnpx -y remixicon-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmremixicon-mcp

Tools

1

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
keywordsstringYesComma-separated keywords to search for icons (e.g., 'summer, sun, beach')

Details

From the project README

RemixIcon MCP

NPM Version NPM License NPM Downloads

English | 简体中文

A lightweight Model Context Protocol (MCP) server that maps icon-focused keywords directly to Remix Icon metadata. Provide concise keywords (up to 20), receive the top 5 matching icon names and metadata – clean architecture with FlexSearch-powered local search.

Features

  • Smart Keyword Input – Supports up to 20 comma-separated keywords while rejecting natural-language sentences for optimal search quality.
  • Fixed Top-5 Results – Returns exactly 5 most relevant icons for focused decision-making.
  • FlexSearch-backed Index – Uses FlexSearch v0.8's document index for high-performance token lookup over the local Remix Icon catalog.
  • Clean Architecture – Domain entities, application use cases, infrastructure adapters, and MCP interface remain isolated for easy testing.
  • CLI Ready – Can be run as a standalone CLI tool via npx remixicon-mcp or integrated into MCP clients.
  • LLM-ready Responses – Returns ranked candidates, matched tokens, and explicit guidance instructing the model to choose exactly one icon.

Quick Start

Installation
# Install as CLI tool globally
npm install -g remixicon-mcp

# Or run directly with npx
npx remixicon-mcp

# For development
pnpm install
pnpm typecheck
pnpm test
Usage
As a Standalone CLI Tool

You can run the MCP server directly via stdio for testing or integration:

# Run with npx
npx remixicon-mcp

# Or if installed globally
remixicon-mcp

Platform Setup

Claude Desktop

Configuration Add the following to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "remix-icon": {
      "command": "npx",
      "args": ["-y", "remixicon-mcp"]
    }
  }
}

Setup Steps

  1. Save the configuration file
  2. Completely quit and restart Claude Desktop
  3. The search_icons tool will be available in your conversations
Claude Code

Option 1: Marketplace Plugin (Recommended)

# In Claude Code, add the marketplace plugin
/plugin marketplace add Remix-Design/remixicon-mcp

Benefits:

  • Automatic installation and updates
  • Complete plugin metadata and versioning
  • Rich discovery with keywords and categorization
  • Full integration with Claude Code's plugin ecosystem

Option 2: Manual Configuration

# Quick command-line setup
claude mcp add --transport stdio remixicon -- npx -y remixicon-mcp

Or manually add to your project's .claude/settings.json:

{
  "mcp": {
    "servers": {
      "remix-icon": {
        "command": "npx",
        "args": ["-y", "remixicon-mcp"]
      }
    }
  }
}

Setup Steps

  1. Choose one of the installation methods above
  2. Restart Claude Code for the changes to take effect
  3. The search_icons tool will be available in your sessions
Codex

Configuration

# Quick command-line setup
codex mcp add remixicon -- npx -y remixicon-mcp

Setup Steps

  1. Run the installation command above
  2. Restart Codex for the changes to take effect
  3. The search_icons tool will be available in your conversations

Available Tools

The server communicates over stdio using JSON-RPC 2.0 via the official @modelcontextprotocol/sdk and exposes a single tool:

search_icons

Input: keywords string (comma-separated, up to 20 keywords)
Output: Top 5 most relevant icons with metadata
Format: Human-readable summary + structured metadata

Example Usage

JSON-RPC Call:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_icons",
    "arguments": {
      "keywords": "layout, grid, design"
    }
  }
}

Sample Response: The server returns the top 5 icons that match your keywords, complete with names, categories, and usage information.

Project Structure

.
├── bin/
│   └── run.cjs                     # CLI entry point for npx execution
├── src/
│   ├── cli/                        # CLI runner implementation
│   ├── bootstrap/                  # Dependency wiring for Clean Architecture boundaries
│   ├── domain/                     # Icon entities and keyword parser
│   ├── application/                # Search use case orchestrating validation and ranking
│   ├── infrastructure/search/      # FlexSearch-backed repository implementation
│   ├── interface/mcp/              # MCP server built with @modelcontextprotocol/sdk
│   └── data/tags.json              # Remix Icon tags for search functionality
├── tests/                          # Vitest suites covering parser and use case behaviour
├── .claude-plugin/
│   └── marketplace.json            # Marketplace metadata for Claude Code plugin discovery
├── package.json                    # pnpm-friendly manifest and scripts
└── tsconfig.json                   # Strict TypeScript configuration with Node typings

Implementation Notes

  • Keywords are parsed with Unicode-aware boundaries, supporting up to 20 comma-separated keywords while rejecting sentence-style inputs.
  • Enhanced detection differentiates between keyword lists (with delimiters) and natural language sentences (space-separated phrases).
  • FlexSearch indexes icon names, tags, usage, and categories; field weights plus token matches drive deterministic scores.
  • Fixed top-5 results provide focused, relevant matches without configuration complexity.
  • The application layer combines parser validation, repository queries, and response formatting so the interface only handles transport concerns.
  • MCP responses include natural-language guidance and machine-readable matches so LLM clients can choose exactly one icon.
  • CLI runner enables standalone execution via npx or global installation for easy integration.

Development Scripts

pnpm typecheck   # Strict TypeScript check (tsc --noEmit)
pnpm test        # Run Vitest suites
pnpm exec biome check --write --unsafe   # Format + fix code with Biome

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.