Design Systems MCP Server

An AI-powered Model Context Protocol (MCP) server providing intelligent access to authoritative design systems knowledge. Powered by Supabase vector search with 188+ curated entries including W3C standards, WCAG guidelines, and design system best practices.

🌐 Live Demo: https://design-systems-mcp.southleft.com/

Features

Core Capabilities

• 🎯 Production Vector Search - Supabase pgvector with OpenAI embeddings for semantic understanding

• 📚 188+ Curated Entries - W3C standards, WCAG 2.2, ARIA practices, and 10+ major design systems

• 🔍 Hybrid Search Architecture - Combines vector similarity with keyword matching (0.15 threshold)

• 🚀 Edge-Optimized - Cloudflare Workers deployment with global distribution

Latest Updates

• ⚡ Streaming Responses - Chat answers stream token-by-token via SSE; first content appears in seconds

• 🏠 Refreshed Landing Page - Hero, MCP endpoint with one-click copy, and a "What's inside" overview

• 🛡️ Source Reliability Badges - Every answer flags Primary / Authoritative / Reference / Example / Community sources

• ✨ 188+ Curated Entries - W3C, WCAG 2.2, ARIA APG, and 10+ major design systems

• 🔧 Production Vector Search - Supabase pgvector with OpenAI embeddings, keyword fallback

• 📖 Universal MCP Client Support - Works with any MCP-capable client (Claude Desktop, Cursor, Windsurf, etc.)

Developer Experience

• 🌐 Zero Setup Required - Public MCP endpoint ready to use

• 🤖 AI Chat Interface - Natural language queries with GPT-4o + streaming responses (SSE) for fast time-to-first-token

• 🧪 Local Development - Complete testing environment with hot reload

• 📝 Comprehensive Docs - Updated setup guides for every major MCP client

Related MCP server: Components Build MCP

Content Library

188+ Curated Entries Including:

Standards & Specifications

• W3C Design Tokens Community Group (DTCG) Specification

• WCAG 2.2 Guidelines (A, AA, AAA levels)

• WAI-ARIA Authoring Practices Guide (APG)

• W3C Web Content Accessibility Guidelines

• W3C Mobile Accessibility at W3C

Design System Resources

• Material Design 3 (Google)

• Fluent Design System (Microsoft)

• Ant Design (Alibaba)

• Carbon Design System (IBM)

• Polaris (Shopify)

• Lightning Design System (Salesforce)

• Atlassian Design System

• Adobe Spectrum

• GitHub Primer

• Shopify Polaris

Tools & Frameworks

• Figma Design System Guides

• Style Dictionary Documentation

• Design Tokens Format Module

• Storybook Best Practices

Methodologies & Best Practices

• Atomic Design principles

• Design Systems Handbook

• Component architecture patterns

• Accessibility implementation guides

Quick Start

Using the Public MCP Server (Recommended)

No installation needed! Connect any MCP client to our live server:

https://design-systems-mcp.southleft.com/mcp

See Connect to MCP Clients section below for detailed setup instructions.

Local Development

1. Clone and Install

   git clone https://github.com/southleft/design-systems-mcp.git
   cd design-systems-mcp
   npm install

2. Configure Environment

   cp .dev.vars.example .dev.vars
   # Edit .dev.vars and add your credentials

3. Start Development Server

   npm run dev

   Server available at: http://localhost:8787

Connect to MCP Clients

Choose your AI coding tool below for setup instructions:

Add via Custom Connector UI (Recommended - No JSON editing!)

1. Open Claude Desktop and navigate to Settings → Connectors

2. Click "Add custom connector" at the bottom of the connectors list

3. Fill in the connector details:

   • Name: Design Systems Assistant (or any name you prefer)

   • URL: https://design-systems-mcp.southleft.com/mcp

4. Click "Add" to save the connector

5. Start using it! The connector will appear in your connectors list with 4 available tools:

   • search_design_knowledge

   • search_chunks

   • browse_by_category

   • get_all_tags

That's it! You can now use the Design Systems Assistant in your Claude Desktop conversations.

Note: Custom connectors are available for Claude Pro, Team, and Enterprise plans.

Quick Setup via CLI:

claude mcp add --transport http design-systems https://design-systems-mcp.southleft.com/mcp

Or manually edit .mcp.json:

{
  "mcpServers": {
    "design-systems": {
      "type": "http",
      "url": "https://design-systems-mcp.southleft.com/mcp"
    }
  }
}

Verify connection:

claude mcp list

Location: ~/.cursor/mcp_config.json or ~/.config/cursor/mcp_config.json

{
  "mcpServers": {
    "design-systems": {
      "url": "https://design-systems-mcp.southleft.com/mcp"
    }
  }
}

Restart Cursor after updating the configuration.

Location: VSCode Settings → Extensions → Cline → MCP Settings

Add to MCP servers configuration:

{
  "design-systems": {
    "url": "https://design-systems-mcp.southleft.com/mcp",
    "description": "Design systems knowledge and best practices"
  }
}

Or add via Command Palette: Cline: Add MCP Server

Reload VSCode after configuration.

Location: VSCode Settings → Extensions → Continue → config.json

{
  "mcpServers": [
    {
      "name": "design-systems",
      "url": "https://design-systems-mcp.southleft.com/mcp",
      "description": "Design systems knowledge base"
    }
  ]
}

Location: ~/.config/zed/settings.json

{
  "mcp": {
    "servers": {
      "design-systems": {
        "url": "https://design-systems-mcp.southleft.com/mcp"
      }
    }
  }
}

For any MCP client supporting remote servers:

Endpoint: https://design-systems-mcp.southleft.com/mcp

Protocol: JSON-RPC 2.0 over HTTP/HTTPS

Transport: Standard MCP transport (stdio, SSE, or HTTP)

To connect to your local development server instead of the public endpoint:

{
  "mcpServers": {
    "design-systems": {
      "url": "http://localhost:8787/mcp"
    }
  }
}

Note: Local server requires running npm run dev first.

Connection Troubleshooting

Server not responding?

• Verify the URL is correct: https://design-systems-mcp.southleft.com/mcp

• Test with curl: curl https://design-systems-mcp.southleft.com/health

• Check your client supports remote MCP servers

Tools not appearing?

• Restart your MCP client after configuration changes

• Check client logs for connection errors

• Verify JSON configuration syntax is correct

Need help?

• Open an issue: GitHub Issues

• Check documentation: Connection Guide

Available MCP Tools

The server provides these tools for AI assistants:

search_design_knowledge

Search the complete knowledge base with semantic understanding.

Parameters:

• query (string, required) - Search query

• category (string, optional) - Filter by category

• tags (array, optional) - Filter by tags

• limit (number, optional) - Max results (default: 15)

Example:

{
  "name": "search_design_knowledge",
  "arguments": {
    "query": "WCAG 2.2 color contrast requirements",
    "category": "guidelines",
    "limit": 5
  }
}

search_chunks

Find specific information within content chunks for detailed answers.

Parameters:

• query (string, required) - Search query

• limit (number, optional) - Max chunks (default: 8)

Example:

{
  "name": "search_chunks",
  "arguments": {
    "query": "W3C DTCG design tokens specification",
    "limit": 3
  }
}

browse_by_category

Browse content organized by category.

Categories: components, tokens, patterns, guidelines, workflows, general

Parameters:

• category (string, required) - Category to browse

get_all_tags

Get all available content tags for filtering and exploration.

API Examples

Direct API Testing

Health Check:

curl https://design-systems-mcp.southleft.com/health

MCP Tools List:

curl -X POST https://design-systems-mcp.southleft.com/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Search Query:

curl -X POST https://design-systems-mcp.southleft.com/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
      "name": "search_chunks",
      "arguments": {"query": "design tokens", "limit": 3}
    }
  }'

AI Chat Interface (streaming):

The /ai-chat endpoint returns a Server-Sent Events stream so content appears progressively. Each event is data: {"t": "<chunk>"}\n\n, terminated by event: done\ndata: {}\n\n.

curl -N -X POST https://design-systems-mcp.southleft.com/ai-chat \
  -H "Content-Type: application/json" \
  -d '{"message":"What are the WCAG 2.2 contrast requirements?"}'

The hosted web UI at / consumes this stream and renders markdown progressively.

Adding Content

Ingest Web Content

# Single URL
npm run ingest:url https://material.io/components/buttons

# Bulk from CSV
npm run ingest:csv urls.csv

# Crawl entire website
npm run crawl:website https://polaris.shopify.com --max-depth 3

Ingest PDF Content

npm run ingest:pdf path/to/design-guide.pdf

Generate Vector Embeddings

npm run ingest:vectors

See Content Ingestion Guide for detailed instructions.

Development

Available Scripts

• npm run dev - Start local development server

• npm run deploy - Deploy to Cloudflare Workers

• npm run ingest:pdf <file> - Ingest PDF content

• npm run ingest:url <url> - Ingest web content

• npm run ingest:csv <file> - Bulk ingest from CSV

• npm run crawl:website <url> - Crawl entire websites

• npm run ingest:vectors - Generate embeddings for all content

• npm run setup:supabase - Initialize Supabase database

• npm run check:duplicates - Check for duplicate content

Project Structure

design-systems-mcp/
├── src/
│   ├── index.ts                    # Main MCP server, transports, tool dispatch, embedded chat UI
│   ├── sse-session.ts              # SSE transport (Durable Object)
│   ├── streamable-http-handler.ts  # Streamable HTTP transport (/mcp)
│   ├── oauth-handler.ts            # OAuth flow
│   └── lib/
│       ├── content-manager.ts      # Content management
│       ├── search-handler.ts       # Vector + keyword search dispatch
│       ├── vector-search.ts        # Supabase vector search
│       ├── source-authority.ts     # Reliability tiers & APG disclaimers
│       └── ... (chunker, formatters, ingestion helpers)
├── content/
│   ├── entries/              # Ingested content (JSON)
│   └── raw/                  # Raw source files
├── supabase/
│   └── migrations/           # SQL schema + RPC functions
├── scripts/
│   ├── ingestion/            # Content ingestion pipeline (URL, PDF, HTML, CSV, crawler)
│   └── build/                # Build helpers (manifest generation)
├── types/
│   └── content.ts           # TypeScript definitions
├── docs/                    # Additional documentation
├── wrangler.jsonc          # Cloudflare Workers config
└── .dev.vars              # Local environment variables

Deployment

Deploy to Cloudflare Workers

1. Login to Cloudflare

   npx wrangler login

2. Set Secrets

   npx wrangler secret put OPENAI_API_KEY
   npx wrangler secret put SUPABASE_URL
   npx wrangler secret put SUPABASE_SERVICE_KEY
   npx wrangler secret put SUPABASE_ANON_KEY

3. Deploy

   npm run deploy

See Deployment Guide for detailed instructions.

Vector Search Architecture

This server uses Supabase for production-grade vector search:

• Database: PostgreSQL with pgvector extension

• Embeddings: OpenAI text-embedding-3-small (1536 dimensions)

• Threshold: 0.15 for optimal recall

• Hybrid Search: Combines semantic vectors with text matching

• Performance: Sub-100ms queries with proper indexing

Statistics:

• 188+ entries in production database

• 761+ content chunks with embeddings

• W3C standards, WCAG guidelines, design system documentation

• Regular updates with new authoritative sources

See Vector Search Setup for architecture details.

Troubleshooting

Common Issues

Vector search not working:

• Check Supabase credentials in environment variables

• Verify database tables exist: npm run setup:supabase

• Check logs: npx wrangler tail

Content not found:

• Verify content exists: npm run check:duplicates

• Check if embeddings generated: Look for embedding field in content entries

• Test search locally: npm run dev and use curl commands

MCP connection fails:

• Verify URL is correct and accessible

• Check client supports remote MCP servers

• Test with curl: curl https://design-systems-mcp.southleft.com/health

• Restart MCP client after configuration changes

See Troubleshooting Guide for detailed solutions.

Documentation

• Connection Guide - Detailed MCP client setup

• Content Ingestion - Adding new content

• Vector Search Setup - Database configuration

• Deployment Guide - Production deployment

• Contributing - How to contribute

• Security - Security best practices

License & Attribution

License: MIT License - Free for personal and commercial use

Content Attribution: This project compiles design systems knowledge from many brilliant creators. All original content remains the intellectual property of their respective authors.

• See CREDITS.md for complete attribution

• Always link back to original sources when sharing insights

• Support original creators by visiting their websites

Security & Privacy

• No sensitive data stored - Only public design system knowledge

• Environment variables use Cloudflare secrets

• Open source and auditable

• Privacy-focused - No user data collection

• Regular security updates

Report security issues to: GitHub Security

Contributing

We welcome contributions! Whether you want to:

• Report bugs or issues

• Suggest new features

• Add more design system content

• Improve the codebase

• Enhance documentation

Please:

1. Check existing issues

2. Open a new issue to discuss

3. Submit a pull request

4. Follow contribution guidelines

Support

• Issues: GitHub Issues

• Discussions: GitHub Discussions

• Live Demo: https://design-systems-mcp.southleft.com/

Acknowledgments

Thanks to the design systems community for sharing knowledge:

• Brad Frost for Atomic Design methodology

• W3C Design Tokens Community Group

• Web Accessibility Initiative (WAI)

• All design teams who openly share their work

• The entire design systems community

See CREDITS.md for the complete list.

Built with ❤️ using Cloudflare Workers and the Model Context Protocol