BrixUI MCP Server
An MCP server that connects AI clients to Figma components, design tokens, and variables from the BrixUI Design System, enabling component browsing, searching, and token retrieval.
README
BrixUI MCP Server
A production-ready Model Context Protocol server for the BrixUI Design System V1.2. Connects AI clients — Claude, ChatGPT, Cursor, Windsurf, Roo Code, Cline, and any MCP-compatible client — directly to your Figma components, design tokens, and variables.
What it does
| Capability | Details |
|---|---|
| List components | Browse all 274+ components organized by category |
| Search components | Fuzzy search by name, category, or description |
| Component details | Full node metadata, auto-layout, variants, fills, effects |
| Design tokens | Colors, spacing, border radius, typography via Variables API |
| MCP Resources | brixui://components, brixui://tokens, brixui://colors, brixui://typography |
Requirements
- Node.js 20+
- A Figma Personal Access Token
Installation
Global install
npm install -g brixui-mcp-server
Or run without installing
npx brixui-mcp-server
Environment Setup
export FIGMA_PERSONAL_ACCESS_TOKEN=your_figma_token_here
To use a different Figma file (optional):
export BRIXUI_FILE_KEY=your_custom_file_key
The default BrixUI file key is 6Gvd4zkjc7K7RdRxkRF5wP.
Create a .env file for local development:
cp .env.example .env
# edit .env and add your token
Client Configuration
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"brixui": {
"command": "npx",
"args": ["brixui-mcp-server"],
"env": {
"FIGMA_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
}
}
Or if installed globally:
{
"mcpServers": {
"brixui": {
"command": "brixui-mcp-server",
"env": {
"FIGMA_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
}
}
ChatGPT Desktop
In ChatGPT Desktop → Settings → MCP Servers → Add Server:
{
"name": "BrixUI Design System",
"command": "npx",
"args": ["brixui-mcp-server"],
"env": {
"FIGMA_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
Cursor
Edit ~/.cursor/mcp.json:
{
"mcpServers": {
"brixui": {
"command": "npx",
"args": ["brixui-mcp-server"],
"env": {
"FIGMA_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
}
}
Roo Code
Edit your Roo Code MCP config (~/.roo/mcp.json or the workspace .roo/mcp.json):
{
"mcpServers": {
"brixui": {
"command": "npx",
"args": ["brixui-mcp-server"],
"env": {
"FIGMA_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
}
}
Windsurf / Cline / other MCP clients
Any client that supports stdio MCP servers can use:
{
"command": "npx",
"args": ["brixui-mcp-server"],
"env": {
"FIGMA_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
Available Tools
| Tool | Description |
|---|---|
list_brix_components |
List all components grouped by category |
search_brix_components |
Search by keyword with optional category filter |
get_brix_component_details |
Full details for a component by node ID |
get_brix_design_tokens |
All color, spacing, radius, and typography tokens |
Available Resources
| URI | Description |
|---|---|
brixui://components |
Full component catalog in plain text |
brixui://tokens |
All design tokens |
brixui://colors |
Color variables with hex values |
brixui://typography |
Typography scale |
Example Prompts
Show all button components from BrixUI
Search for card components in BrixUI
Get the full details of BrixUI component with nodeId 1958:62429
What are all the color tokens in BrixUI? Generate a Tailwind config from them.
Show me the spacing scale from BrixUI and generate CSS custom properties for it
Explain the auto-layout structure of this BrixUI navigation component: <nodeId>
Generate a React component using BrixUI design tokens for a pricing card
What typography styles does BrixUI use? Create a matching Tailwind typography config.
Development
git clone https://github.com/multicomak/BrixUI-MCP.git
cd BrixUI-MCP
npm install
cp .env.example .env
# add your FIGMA_PERSONAL_ACCESS_TOKEN to .env
npm run dev # watch mode
npm run build # production build
npm run typecheck # type checking only
Architecture
src/
├── index.ts # MCP server, tools, resources wiring
├── figma/
│ ├── client.ts # Figma REST API client
│ ├── types.ts # Full TypeScript types for all Figma structures
│ └── cache.ts # In-memory cache (5-min TTL)
├── tools/
│ ├── listComponents.ts
│ ├── searchComponents.ts
│ ├── componentDetails.ts
│ └── designTokens.ts
├── resources/
│ ├── components.ts
│ ├── tokens.ts
│ └── typography.ts
├── utils/
│ ├── env.ts # Token validation and env reading
│ └── logger.ts # Clean stderr logging
└── constants/
└── config.ts # Base URLs, defaults, TTL
License
MIT
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.