HeroUI MCP Server

A high-quality, open-source Model Context Protocol (MCP) server that provides AI agents with comprehensive context and tooling for the HeroUI component library. This server bridges AI systems and HeroUI, enabling intelligent assistance for developers working with HeroUI components.

🚀 Features

• Component Discovery: List and explore all available HeroUI components
• Documentation Access: Retrieve comprehensive component documentation and usage examples
• API Reference: Access detailed component props, slots, and data attributes
• Accessibility Information: Get accessibility guidelines and best practices for each component
• Usage Patterns: Learn common implementation patterns and best practices
• TypeScript Support: Full TypeScript support with comprehensive type definitions
• Caching System: Efficient Git-based caching for fast documentation retrieval
• RESTful API: Clean HTTP endpoints for easy integration

📋 Prerequisites

• Node.js 18.0 or higher
• pnpm (recommended) or npm
• Git (for repository caching)
• Bun (optional, recommended for faster development) or tsx for TypeScript execution

🛠️ Installation

From Source

1. Clone the repository:

   git clone https://github.com/T-Hash06/heroui-mcp.git
   cd heroui-mcp
   

2. Install dependencies:

   pnpm install
   

3. Build the project:

   pnpm build
   

4. Start the server:

   pnpm start
   

The server will start on http://localhost:3000 by default.

🎯 Quick Start

Basic Usage

Once the server is running, the best way to interact with it is through the MCP Inspector tool, which provides a user-friendly interface for exploring and testing MCP servers.

1. Install the MCP Inspector:

   npx @modelcontextprotocol/inspector
   

2. Connect to your server:

   • Open the MCP Inspector in your browser
   • Add your server URL: http://localhost:3000
   • Explore the available tools and resources interactively

Available Tools

The server provides the following MCP tools:

Example: Exploring Components

Using the MCP Inspector, you can:

1. Browse available tools - See all component-related tools in a visual interface
2. Test tools interactively - Run tools like list_components or get_component_docs with real-time results
3. Explore component data - Get detailed information about any HeroUI component
4. View formatted output - See documentation and API information in a readable format

The MCP Inspector provides the best experience for exploring the server's capabilities without needing to write code or use command-line tools.

🏗️ Development

Development Setup

1. Install dependencies:

   pnpm install
   

2. Start development server (choose one option):

   Option A: Using Bun (recommended for faster startup)

   # Install Bun if you don't have it
   curl -fsSL https://bun.sh/install | bash
   
   # Start development server
   pnpm dev
   

   Option B: Using tsx (if you prefer Node.js)

   # Install tsx globally or use npx
   npm install -g tsx
   
   # Run directly with tsx
   npx tsx src/index.ts
   

3. For production deployment:

   # Build the project
   pnpm build
   
   # Start production server
   pnpm start
   

4. Run tests:

   pnpm test
   

5. Format code:

   pnpm format
   

6. Check code quality:

   pnpm check
   

Project Structure

src/
├── app.ts                # Main application setup
├── index.ts              # Entry point
├── cache/                # Git caching system
├── config/               # Configuration management
├── http/                 # HTTP server and routes
├── resources/            # MCP resources
├── server/               # MCP server factory
├── tools/                # MCP tools implementation
│   └── components/       # HeroUI component tools
├── transport/            # Session management
├── types/                # TypeScript type definitions
└── utils/                # Utility functions

Available Scripts

Development vs Production

• Development: Use pnpm dev (Bun) or npx tsx src/index.ts for fast TypeScript execution
• Production: Use pnpm build then pnpm start for optimized compiled JavaScript

🔧 Configuration

The server can be configured through environment variables or configuration files:

Environment Variables

# Server configuration
PORT=3000
HOST=localhost

# Cache configuration
CACHE_DIR=./cache
REPO_URL=https://github.com/heroui-inc/heroui.git
BRANCH=main

Configuration Files

• src/config/server.config.ts - Server configuration
• src/config/cache.config.ts - Cache configuration

🧪 Testing

The project uses Vitest for testing:

# Run all tests
pnpm test

# Run tests once
pnpm test:run

# Run tests with coverage
pnpm test:coverage

# Run specific test file
pnpm test src/tools/components/list-components.test.ts

🤝 Contributing

Quick Contribution Guide

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make your changes
4. Run quality checks: pnpm check
5. Commit your changes: git commit -m 'Add amazing feature'
6. Push to the branch: git push origin feature/amazing-feature
7. Open a Pull Request

Development Standards

• Follow Conventional Commits
• Maintain TypeScript strict mode compliance
• Write tests for new functionality
• Ensure all quality checks pass (pnpm check)
• Document new features and APIs

🐞 Troubleshooting

Common Issues

Server won't start

• Check if the port is already in use
• Verify Node.js version (18.0+ required)
• Ensure all dependencies are installed

Cache initialization fails

• Check internet connection for Git repository access
• Verify Git is installed and accessible
• Check repository URL and branch configuration

Tool execution errors

• Ensure the HeroUI repository cache is initialized
• Check component name spelling and case sensitivity
• Verify the requested component exists in the documentation

Debug Mode

Enable debug logging:

NODE_ENV=development pnpm dev

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• HeroUI - The amazing component library this server supports
• Model Context Protocol - The protocol specification

🔗 Links

• HeroUI Documentation
• Model Context Protocol
• Project Issues
• Project Discussions

---