ui-ux-pro-mcp
๐จ AI-powered UI/UX design intelligence - 1519+ curated design resources through MCP | React, Vue, Next.js, Flutter & more
README
๐จ UI/UX Pro MCP Server
AI-powered UI/UX design intelligence โ Instantly access 1,700+ curated design resources through natural language search.
โจ Features
| Feature | Details |
|---|---|
| ๐ 1,700+ Documents | Curated design knowledge across 11 domains |
| ๐ง 6 Tools | Consolidated search tools optimized for LLM performance |
| โก BM25 Ranking | Fast, relevant search results using industry-standard text ranking |
| ๐ Universal | Works with VS Code, Claude Desktop, Cursor, and any MCP-compatible client |
| ๐ฏ 12 Frameworks | Stack-specific guidelines for React, Vue, Next.js, Flutter, SwiftUI, Jetpack Compose, and more |
๐ Quick Start
Option 1: NPX (Recommended)
npx ui-ux-pro-mcp
Option 2: Global Install
npm install -g ui-ux-pro-mcp
ui-ux-pro-mcp
Option 3: From Source
# Clone the repository
git clone https://github.com/redf0x1/ui-ux-pro-mcp.git
cd ui-ux-pro-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Run the server
npm start
โ๏ธ MCP Configuration
VS Code / Cursor
Add to your MCP settings (settings.json or mcp.json):
Option A: Using NPX (Recommended - No Installation Required)
{
"mcpServers": {
"ui-ux-pro": {
"command": "npx",
"args": ["ui-ux-pro-mcp", "--stdio"]
}
}
}
Option B: Using Global Install
{
"mcpServers": {
"ui-ux-pro": {
"command": "ui-ux-pro-mcp",
"args": ["--stdio"]
}
}
}
Option C: From Source
{
"mcpServers": {
"ui-ux-pro": {
"command": "node",
"args": [
"/path/to/ui-ux-pro-mcp/dist/index.js",
"--stdio"
]
}
}
}
Configuration file locations:
| Platform | Path |
|---|---|
| macOS | ~/Library/Application Support/Code/User/mcp.json |
| Windows | %APPDATA%\Code\User\mcp.json |
| Linux | ~/.config/Code/User/mcp.json |
Claude Desktop
Add to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Option A: Using NPX (Recommended - No Installation Required)
{
"mcpServers": {
"ui-ux-pro": {
"command": "npx",
"args": ["ui-ux-pro-mcp", "--stdio"]
}
}
}
Option B: Using Global Install
{
"mcpServers": {
"ui-ux-pro": {
"command": "ui-ux-pro-mcp",
"args": ["--stdio"]
}
}
}
Option C: From Source
{
"mcpServers": {
"ui-ux-pro": {
"command": "node",
"args": [
"/path/to/ui-ux-pro-mcp/dist/index.js",
"--stdio"
]
}
}
}
๐ง Available Tools
| Tool | Documents | Description |
|---|---|---|
search_ui_styles |
85 | UI design styles (Glassmorphism, Minimalism, Brutalism, etc.) with colors, effects, and use cases |
search_colors |
121 | Color palettes for industries (SaaS, Healthcare, Fintech) with hex codes |
search_typography |
74 | Font pairings with Google Fonts imports and Tailwind configs |
search_charts |
37 | Chart types with implementation recommendations for dashboards |
search_ux_guidelines |
115 | UX best practices, do's and don'ts, accessibility (WCAG) |
search_icons |
176 | Curated Lucide icons with import codes and use cases |
search_landing |
49 | Landing patterns, Bento Grids (Config & Maps), Responsive Strategy |
search_products |
114 | Product type design recommendations per industry |
search_prompts |
39 | AI prompt templates with CSS snippets and implementation checklists |
search_stack |
696 | Framework-specific guidelines (React, Vue, Next.js, Flutter, etc.) |
search_all |
All | Unified search across all design domains |
get_design_system |
โ | Generate complete design system with colors, typography, UI style, and layout in one call |
AI-Optimized Query Processing
The get_design_system tool uses intelligent query processing optimized for AI model consumers:
Position-Weighted Intent Classification
Queries are processed left-to-right with multi-word phrase priority:
- Multi-word phrases first: "landing page", "admin panel", "hero section" have higher priority
- Then single words: "dashboard", "landing", "analytics"
- Position matters: Earlier keywords get higher confidence (5% penalty per word position)
Examples:
| Query | Detected Intent | Reason |
|---|---|---|
| "SaaS landing page dashboard" | landing | "landing page" phrase found |
| "dashboard for SaaS landing" | dashboard | "dashboard" is first |
| "admin panel with hero section" | dashboard | "admin panel" phrase beats "hero" |
| "website for fintech startup" | landing | "website" maps to landing |
AI-Optimized Output Structure
The _meta field provides transparency for AI models:
{
"_meta": {
"query_interpretation": "SaaS landing page with glassmorphism (dark mode)",
"detected_intent": "landing",
"intent_confidence": 0.85,
"matched_keyword": "landing page",
"keyword_position": 1,
"warnings": []
}
}
Dark Mode Color Parsing
When mode: "dark", the tool:
- Searches for dark-mode compatible palettes
- Parses
Dark_Mode_ColorsJSON from the database - Replaces palette colors with dark mode equivalents
- Includes both light and dark mode palettes in response
Code-Ready Snippets
Colors include ready-to-paste code:
{
"colors": {
"css_variables": "--primary: #0066FF; --background: #0A0E14; --text: #E5E5E5;",
"tailwind_config": "colors: { primary: '#0066FF', ... }"
}
}
Layout Source Indicator
The layout.source field tells AI models where the layout recommendation came from:
"landing"- From landing page patterns database"dashboard"- From product's dashboard style recommendation
๐ฌ Example Prompts
Use these with Claude, Cursor, or any MCP-compatible AI:
๐จ Design Systems
"What UI style works best for a fintech dashboard?"
"Give me a color palette for a healthcare app"
"Find modern font pairings for a SaaS landing page"
๐ Data Visualization
"What chart type should I use for time-series data?"
"How do I make charts accessible?"
๐ฅ๏ธ Landing Pages
"Show me landing page patterns for SaaS conversion"
"What sections should a pricing page have?"
๐ฑ UX Guidelines
"What are mobile touch target best practices?"
"Show me accessibility guidelines for forms"
โ๏ธ Framework-Specific
"React hooks best practices"
"Vue 3 composition API patterns"
"Next.js App Router guidelines"
"Flutter state management recommendations"
๐ Data Sources
This server aggregates curated design intelligence from multiple domains:
| Domain | File | Count | Content |
|---|---|---|---|
| Styles | styles.csv |
85 | UI design trends, effects, animations |
| Colors | colors.csv |
121 | Industry-specific color palettes |
| Typography | typography.csv |
74 | Font pairings and configurations |
| Charts | charts.csv |
37 | Data visualization recommendations |
| UX Guidelines | ux-guidelines.csv |
115 | Usability and accessibility best practices |
| Icons | icons.csv |
176 | Lucide icon recommendations |
| Landing | landing.csv |
49 | Patterns, Bento Layout Maps, Responsive Strategy |
| Products | products.csv |
114 | Industry design recommendations |
| Prompts | prompts.csv |
39 | AI prompt templates |
| Stacks | stacks/*.csv |
766 | Framework-specific guidelines (12 stacks) |
Available Framework Stacks:
flutter ยท html-tailwind ยท jetpack-compose ยท nextjs ยท nuxt-ui ยท nuxtjs ยท react-native ยท react ยท shadcn ยท svelte ยท swiftui ยท vue
๐ API Reference
Common Input Parameters
All search tools accept:
| Parameter | Type | Default | Description |
|---|---|---|---|
query |
string | required | Natural language search query |
max_results |
number | 3 | Maximum results to return (1-50) |
search_stack Additional Parameter
| Parameter | Type | Description |
|---|---|---|
stack_name |
string | Framework name: react, vue, nextjs, flutter, swiftui, etc. |
Response Format
All tools return results in this structure:
{
results: Array<{
id: string; // Document identifier
score: number; // BM25 relevance score
type: string; // Document type (style, color, etc.)
data: object; // Full document data
}>;
total: number; // Total results returned
query: string; // Original search query
}
Error Response
{
error: string; // Error description
}
๐ ๏ธ Development
Build Commands
# Build TypeScript to JavaScript
npm run build
# Development mode with hot reload
npm run dev
# Start production server (stdio mode)
npm start
# Start HTTP server for testing
npm run start:http
Testing
# Run test suite
npm test
HTTP Mode for Testing
The server can run in HTTP mode for testing without MCP clients:
# Start HTTP server on port 3456
PORT=3456 npm run start:http
Then test with curl:
curl -X POST http://localhost:3456/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"search_colors","arguments":{"query":"fintech"}},"id":1}'
Project Structure
ui-ux-pro-mcp/
โโโ src/
โ โโโ index.ts # MCP server entry point
โ โโโ data/
โ โ โโโ loader.ts # CSV data loading utilities
โ โโโ search/
โ โ โโโ bm25.ts # BM25 search implementation
โ โโโ tools/
โ โโโ index.ts # Tool exports
โ โโโ handlers.ts # Search handlers
โโโ data/
โ โโโ *.csv # Design domain data files
โ โโโ stacks/ # Framework-specific guidelines
โโโ dist/ # Compiled JavaScript output
๐ Environment Variables
| Variable | Default | Description |
|---|---|---|
MCP_LOG_LEVEL |
info |
Log level (debug, info, warn, error) |
PORT |
3000 |
HTTP server port (when using HTTP transport) |
MCP_HTTP_HOST |
localhost |
HTTP server host |
๐ HTTP Transport Mode
For development and testing, you can run the server in HTTP mode:
# Start HTTP server
npm run start:http
# Server runs at http://localhost:3000
# SSE endpoint: GET /sse
# Message endpoint: POST /message
Test with curl:
curl -X POST http://localhost:3000/message \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_colors","arguments":{"query":"fintech"}}}'
โ Troubleshooting
MCP Connection Issues
"Cannot find MCP server"
- Ensure
npm run buildcompleted successfully - Check the path in your MCP config points to
dist/index.js - Verify Node.js is in your PATH
"No results returned"
- Try broader search terms
- Use
search_allfor cross-domain queries - Check if the domain matches your query type
"Server not responding"
- Restart VS Code/Claude Desktop
- Check terminal for error messages
- Verify the server process is running
Common Queries
| Need | Best Tool |
|---|---|
| Color palettes | search_styles with domain: "color" |
| UI components | search_styles with domain: "style" |
| Best practices | search_patterns with type: "ux" |
| Icons | search_components with type: "icon" |
| Framework tips | search_stack |
| Everything | search_all |
๏ฟฝ Contact
๏ฟฝ๐ License
MIT License โ see LICENSE for details.
๐ Acknowledgments
- Original Data: Based on nextlevelbuilder/ui-ux-pro-max-skill
- MCP SDK: Built with @modelcontextprotocol/sdk
- Search: BM25 ranking algorithm for relevance scoring
<div align="center">
โญ Star this repo if you find it useful!
Made with โค๏ธ by redf0x1
</div>
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.