BrowserStack Design Stack MCP Server
A standalone MCP server that provides AI assistants with comprehensive access to BrowserStack's design system components, enabling component search, detailed prop analysis, and usage examples from Storybook.
README
BrowserStack Design Stack MCP Server
A standalone Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to BrowserStack's design system components. This server extracts and serves structured metadata about React components from both source code (using react-docgen) and Storybook files.
Features
- 🔍 Component Search: Search for components by name, functionality, or use case
- 📖 Detailed Component Info: Get comprehensive prop information from both react-docgen and Storybook
- 📋 Component Listing: Browse all available components in the design system
- 🔍 Props Analysis: Compare prop information between different sources
- 🎯 Real Usage Examples: Extract actual usage examples from Storybook stories
- ⚙️ Configurable Paths: Use environment variables to point to any design system location
Installation
- Clone or copy this repository to your desired location (outside the frontend repo)
- Install dependencies:
npm install
- Configure the design system path:
cp .env.example .env
# Edit .env and set DESIGN_STACK_PATH to your design system location
Configuration
Set the following environment variables in your .env file:
# Required: Path to your design system package
DESIGN_STACK_PATH=/path/to/your/design-stack
# Optional: Enable debug logging
DEBUG=false
# Optional: Enable caching (future feature)
ENABLE_CACHE=false
Usage
As an MCP Server
Start the server for use with MCP-compatible tools:
npm start
Testing Locally
Run the test script to verify functionality:
npm test
Available MCP Tools
The server provides these tools to AI assistants:
1. search_components
Search for components by name or functionality.
Parameters:
query(string): Search termlimit(number, optional): Max results (default: 10)
2. get_component_info
Get detailed information about a specific component.
Parameters:
componentName(string): Name of the component (e.g., "Accordion", "Button")
3. list_all_components
Get a list of all available components in the design system.
Parameters: None
4. analyze_component_props
Compare prop information between react-docgen and Storybook sources.
Parameters:
componentName(string): Name of the component to analyze
Integration with AI Tools
Claude Desktop (MCP)
Add this configuration to your Claude Desktop MCP settings:
{
"mcpServers": {
"design-stack": {
"command": "node",
"args": ["/path/to/design-stack-mcp-server/src/index.js"],
"env": {
"DESIGN_STACK_PATH": "/path/to/your/design-stack"
}
}
}
}
VS Code Extensions
The server can be integrated with VS Code extensions that support MCP protocol.
How It Works
Component Analysis
The server analyzes components from two sources:
-
React-docgen: Extracts props from component source code, including:
- Prop types and names
- Required/optional status
- Default values
- JSDoc descriptions
-
Storybook argTypes: Extracts props from Storybook configuration:
- Rich descriptions
- Control types
- Default values
- Type summaries
Example Extraction
The server extracts real usage examples from Storybook stories:
- Template-based stories: Extracts simple props from
.argsconfigurations - Functional stories: Extracts component usage from exported functions
- Complex examples: Handles nested JSX and complex prop values
Data Merging
Props from both sources are intelligently merged:
- Storybook descriptions are preferred (usually more comprehensive)
- Type information is combined from both sources
- Source tracking shows where each piece of information originated
Example Output
# Accordion
**Description:** The Accordion component provides a way to toggle the visibility of content sections.
## Props:
• **defaultOpen**: boolean [storybook]
Determines whether the Accordion is to be open by default.
• **children**: node (required) [react-docgen, storybook]
The content to be rendered inside the Accordion.
• **wrapperClassName**: string [storybook]
A custom CSS class name to style the wrapper of the Accordion component.
## Examples from Storybook:
**InteractiveAccordion**:
```jsx
<Accordion defaultOpen={true} />
InteractiveAccordion example from Storybook
File Locations:
- Component: /path/to/design-stack/modules/Accordion/index.jsx
- Storybook: /path/to/design-stack/modules/Accordion/Accordion.stories.jsx
## Development
### Project Structure
design-stack-mcp-server/ ├── src/ │ ├── index.js # MCP server implementation │ └── component-analyzer.js # Component analysis logic ├── .env.example # Environment configuration template ├── .env # Local environment configuration ├── package.json # Dependencies and scripts └── README.md # This file
### Adding New Features
The server is designed to be extensible. You can add new tools by:
1. Adding new functions to `component-analyzer.js`
2. Registering new tools in `index.js` using `server.tool()`
3. Testing with the test script
### Debug Mode
Enable debug logging to troubleshoot issues:
```bash
echo "DEBUG=true" >> .env
npm start
Requirements
- Node.js 18+
- Design system with React components
- Storybook files (optional but recommended for better descriptions)
License
MIT License - see package.json for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。