
MCP Design System Bridge
Enables bidirectional synchronization between IDEs and Figma for Design System management, allowing developers to generate React components and synchronize design tokens, icons, and components across platforms.
README
MCP Design System Bridge
A Model Context Protocol (MCP) for bidirectional synchronization between IDE and Figma for Design System management.
Features
1. React Component Generation
- Generate React components with TypeScript
- Support for variants using class-variance-authority
- Interactive states (hover, focus, disabled, loading)
- Forwarded refs for composition
- Styled with Tailwind CSS + CSS Modules
- Complete JSDoc documentation
- Automatic Storybook stories
- React Testing Library tests
- Barrel exports
2. Figma Component Generation
- Create component frames
- Apply design tokens
- Generate variants automatically
- Create responsive auto-layout
- Integrated documentation
3. Figma → IDE Extraction
- Design tokens (colors, typography, shadows, spacing, borders)
- Icons (optimized SVG, multiple formats)
- Images (PNG, JPG, WebP with optimization)
- Components (structure, props, variants)
4. IDE → Figma Synchronization
- React component analysis
- Props and variants extraction
- Tailwind/CSS style analysis
- Interactive state detection
- Design token mapping
5. Bidirectional Synchronization
- Automatic change detection
- Confirmation prompts
- Visual diff
- Sync history
- Rollback capability
Installation
npm install mcp-design-system-bridge
Configuration
Create a .mcp-config.json
file in your project root:
{
"figma": {
"accessToken": "your-figma-access-token",
"fileId": "your-figma-file-id"
},
"paths": {
"components": "src/components",
"tokens": "src/tokens",
"icons": "src/icons",
"assets": "src/assets"
},
"generation": {
"useTailwind": true,
"useCSSModules": true,
"useStorybook": true,
"useTests": true
}
}
Usage
Generate React Component
import { MCP } from 'mcp-design-system-bridge';
const mcp = new MCP({
figmaAccessToken: 'your-token',
figmaFileId: 'your-file-id'
});
const component = await mcp.generateReactComponent({
name: 'Button',
description: 'A button component',
props: [
{
name: 'variant',
type: "'primary' | 'secondary' | 'tertiary'",
required: true
},
{
name: 'size',
type: "'sm' | 'md' | 'lg'",
required: true
}
],
variants: [
{
name: 'primary',
props: {
backgroundColor: 'var(--color-primary-500)',
color: 'var(--color-white)'
}
}
]
});
Extract from Figma
const assets = await mcp.extractFromFigma('node-id');
console.log(assets.tokens);
console.log(assets.components);
console.log(assets.icons);
console.log(assets.images);
Sync to Figma
const result = await mcp.syncToFigma({
components: [/* React components */],
tokens: {/* Design tokens */}
});
Sync from Figma
const result = await mcp.syncFromFigma({
added: [/* New components */],
modified: [/* Modified components */],
deleted: [/* Deleted components */],
conflicts: [/* Conflicts */]
});
Project Structure
design-system/
├── tokens/
│ ├── colors.json
│ ├── typography.json
│ ├── spacing.json
│ └── shadows.json
├── components/
│ ├── Button/
│ │ ├── Button.tsx
│ │ ├── Button.types.ts
│ │ ├── Button.stories.tsx
│ │ ├── Button.test.tsx
│ │ └── index.ts
│ ├── Input/
│ │ ├── Input.tsx
│ │ ├── Input.types.ts
│ │ ├── Input.hooks.ts
│ │ ├── Input.stories.tsx
│ │ ├── Input.test.tsx
│ │ └── index.ts
│ └── Card/
├── hooks/
│ ├── useDesignSystem.ts
│ └── useTheme.ts
├── icons/
├── assets/
├── docs/
└── .mcp-config.json
Development
Prerequisites
- Node.js 18+
- npm 8+
- Figma account with access token
- React 18+ project
Setup
- Clone the repository
- Install dependencies:
npm install
- Create
.mcp-config.json
with your Figma credentials - Start development:
npm run dev
Testing
npm test
Building
npm run build
Contributing
- Fork the repository
- Create your feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
MIT
Support
For support, please open an issue in the GitHub repository.
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.