design-token-bridge-mcp
Translates design tokens across platforms — extracts from Tailwind/CSS/Figma and generates native themes for Material 3, SwiftUI, and CSS variables with WCAG contrast validation.
README
design-token-bridge-mcp
<a href="https://glama.ai/mcp/servers/kenneives/design-token-bridge-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/kenneives/design-token-bridge-mcp/badge" /> </a>
An MCP server that translates design tokens between platforms. Extract tokens from Tailwind, CSS, Figma, or W3C DTCG format — then generate native themes for Material 3 (Kotlin), SwiftUI (with Liquid Glass), Tailwind, and CSS Variables.
Built for the v0 → Figma → Claude Code design pipeline.
┌──────────────┐ ┌──────────────┐ ┌────────────────────────┐
│ Tailwind │ │ │ │ Material 3 (Kotlin) │
│ CSS Vars │────▶│ Universal │────▶│ SwiftUI (Swift) │
│ Figma Vars │ │ Token │ │ Tailwind Config │
│ W3C DTCG │ │ Schema │ │ CSS Variables │
└──────────────┘ └──────────────┘ └────────────────────────┘
Extractors Bridge Generators
Install
From npm
npm install -g design-token-bridge-mcp
From source
git clone https://github.com/kenneives/design-token-bridge-mcp.git
cd design-token-bridge-mcp
npm install && npm run build
Configure with Claude Code
Add to your Claude Code MCP settings (~/.claude/settings.json or project .mcp.json):
{
"mcpServers": {
"design-token-bridge": {
"type": "stdio",
"command": "npx",
"args": ["-y", "design-token-bridge-mcp"]
}
}
}
Or if installed from source:
{
"mcpServers": {
"design-token-bridge": {
"type": "stdio",
"command": "node",
"args": ["/path/to/design-token-bridge-mcp/build/index.js"]
}
}
}
Tools (9 total)
Extractors — Input → Universal Tokens
| Tool | Input | Description |
|---|---|---|
extract_tokens_from_tailwind |
tailwind.config.js content |
Parses colors, fontSize, spacing, borderRadius, boxShadow |
extract_tokens_from_css |
CSS file content | Extracts --color-*, --space-*, --radius-*, --shadow-* custom properties |
extract_tokens_from_figma_variables |
Figma Variables API JSON | Parses COLOR, FLOAT types, resolves aliases, handles multi-mode |
extract_tokens_from_json |
W3C DTCG format JSON | Parses $value/$type/$description, resolves {aliases}, handles groups |
Generators — Universal Tokens → Output
| Tool | Output | Description |
|---|---|---|
generate_material3_theme |
Kotlin (Jetpack Compose) | lightColorScheme(), Typography, Shapes with M3 naming |
generate_swiftui_theme |
Swift (SwiftUI) | Color extensions, Font structs, optional Liquid Glass (iOS 26+) |
generate_tailwind_config |
tailwind.config.js |
Theme extend block with rem units, ESM or CJS |
generate_css_variables |
CSS custom properties | :root block with light/dark mode via prefers-color-scheme |
Validation
| Tool | Description |
|---|---|
validate_contrast |
WCAG AA/AAA contrast checking for color pairs with pass/fail + ratios |
Universal Token Schema
All tools speak this common format:
{
"colors": {
"primary": { "value": "#6750A4", "description": "Brand primary", "category": "primary" }
},
"typography": {
"display-large": { "fontSize": 57, "lineHeight": 64, "fontWeight": 400, "fontFamily": "Inter" }
},
"spacing": { "xs": 4, "sm": 8, "md": 16 },
"radii": { "sm": 8, "md": 12, "lg": 16 },
"elevation": {
"low": {
"shadowColor": "#000000",
"shadowOffset": { "x": 0, "y": 2 },
"shadowRadius": 4,
"shadowOpacity": 0.1
}
},
"motion": {
"fast": { "duration": 150, "easing": "ease-out" }
}
}
Example: Full Pipeline
1. Extract tokens from a Tailwind config
Use extract_tokens_from_tailwind with the contents of my tailwind.config.js
2. Generate native themes from the extracted tokens
Take those tokens and run them through:
- generate_tailwind_config (for the web app)
- generate_material3_theme (for Android)
- generate_swiftui_theme with liquidGlass=true (for iOS)
- generate_css_variables (for a vanilla CSS fallback)
3. Validate accessibility
Run validate_contrast on those tokens at AAA level
Example Output
See the examples/qt-games/ directory for a complete responsive landing page built entirely from MCP-generated tokens, including:
qt-games-tokens.json— extracted universal tokenstailwind.config.js— generated Tailwind configvariables.css— generated CSS custom propertiescontrast-report.json— WCAG validation (AAA pass)index.html+styles.css— responsive landing page using the generated tokens
v0 + Figma Free Tier Setup
This MCP works with free tiers of both v0 and Figma. See the setup guides:
- v0 Setup Guide — free tier signup, web UI workflow
- Figma Setup Guide — free tier MCP config (6 calls/month)
- Claude Code Setup — full pipeline configuration
- Token Extraction Guide — manual extraction when APIs aren't available
Tech Stack
- TypeScript + Node.js
- @modelcontextprotocol/sdk v1.x (stdio transport)
- Zod for schema validation
- Zero heavyweight dependencies — no Babel, no PostCSS, no Style Dictionary
Tests
# 91 unit tests
npm test
# 31 Playwright visual/responsive tests
npm run test:e2e
Contributing
See CONTRIBUTING.md for development setup, project structure, and PR guidelines.
License
MIT — see LICENSE.
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.