Magic Patterns MCP Server
Enables AI assistants to generate UI components and web interfaces from natural language descriptions using the Magic Patterns API.
README
Magic Patterns MCP Server
⚠️ Please use the official Magic Patterns MCP here: Magic Patterns MCP ⚠️
This is original inspiration behind the official MCP. We would recommend everyone to use the official MCP which does not require an API key.
A Model Context Protocol (MCP) server that provides tools for creating UI designs and components using the Magic Patterns API. This server enables AI assistants to generate React components, HTML/CSS layouts, and complete web interfaces through natural language prompts.
Features
- Create Design Tool: Generate UI components and layouts from text descriptions
- Multiple Frameworks: Support for React, HTML/Tailwind, ShadCN, Chakra UI, and Mantine
- Quality Modes: Choose between 'fast' for quick iterations or 'best' for high-quality results
- Flexible Input: Accept design descriptions, existing code to modify, or any design request
- Complete Output: Get source files, compiled assets, preview URLs, and editor links
Installation & Usage
With Bun (Recommended)
# Run directly from source
bun run src/main.ts
# Build and run binary
bun run build
./dist/magic-patterns-mcp
With Docker
# Build the image
docker build -t magic-patterns-mcp .
# Run the server
docker run --rm -i magic-patterns-mcp
With NPM (when published)
npx magic-patterns-mcp
Claude Desktop Integration
Add this MCP server to your Claude Desktop configuration:
{
"mcpServers": {
"magic-patterns-mcp": {
"command": "bun",
"args": ["run", "/path/to/magic-patterns-mcp/src/main.ts"],
"env": {
"MAGIC_PATTERNS_API_KEY": "your-api-key-here"
}
}
}
}
Or if using the binary:
{
"mcpServers": {
"magic-patterns-mcp": {
"command": "/path/to/magic-patterns-mcp/dist/magic-patterns-mcp",
"env": {
"MAGIC_PATTERNS_API_KEY": "your-api-key-here"
}
}
}
}
Environment Variables
MAGIC_PATTERNS_API_KEY: Your Magic Patterns API key (required)
Available Tools
create_design
Creates a new design pattern using the Magic Patterns API.
Parameters:
prompt(required): The design request - can be a description, existing React code to modify, or any design requestmode(optional):"best"(default): Higher quality results, recommended for most use cases"fast": Quick generation for simple fixes or time-sensitive requests
presetId(optional): Framework/styling preset (default: "html-tailwind")"html-tailwind": HTML with Tailwind CSS"shadcn-tailwind": ShadCN components with Tailwind"chakraUi-inline": Chakra UI components"mantine-inline": Mantine components
Returns:
- Design ID and URLs (editor, preview)
- Source files (React/HTML/CSS)
- Compiled assets
- Chat conversation history
Development
Prerequisites
- Bun runtime
- Magic Patterns API key
Setup
# Clone the repository
git clone <repository-url>
cd magic-patterns-mcp
# Install dependencies
bun install
# Set your API key
export MAGIC_PATTERNS_API_KEY="your-api-key"
# Run in development mode
bun run dev
Building
# Create binary executable
bun run build
# The binary will be created at ./dist/magic-patterns-mcp
Docker Development
# Build development image
docker build -f Dockerfile.alternative -t magic-patterns-mcp:dev .
# Run with API key
docker run --rm -i -e MAGIC_PATTERNS_API_KEY="your-key" magic-patterns-mcp:dev
Project Structure
magic-patterns-mcp/
├── src/
│ ├── main.ts # MCP server entry point
│ └── MagicPatterns.ts # Magic Patterns API integration
├── scripts/
│ └── copy-package-json.ts # Build helper
├── dist/ # Compiled binary output
├── Dockerfile # Production container
├── Dockerfile.alternative # Development container
└── package.json
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Related
- Magic Patterns - UI component generation platform
- Model Context Protocol - Protocol specification
- Claude Desktop - AI assistant with MCP support
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.