@depthark/css-first
This server integrates with Mozilla Developer Network (MDN) documentation to suggest CSS properties, check browser support, and provide implementation guidance with user consent mechanisms.
Tools
suggest_css_solution
Suggests CSS-first solutions for UI implementation tasks by searching MDN documentation. Provides detailed CSS property information, browser support, and asks for user consent before recommending usage.
check_css_browser_support
Checks browser support for specific CSS properties using MDN data and provides detailed compatibility information.
get_css_property_details
Retrieves comprehensive information about a CSS property from MDN documentation including syntax, examples, and use cases.
confirm_css_property_usage
Confirms user consent for using a specific CSS property and provides implementation guidance.
README
MCP CSS First
An MCP (Model Context Protocol) server that provides CSS-first solutions for UI implementation tasks. This server integrates with Mozilla Developer Network (MDN) documentation to suggest CSS properties, check browser support, and provide implementation guidance with user consent mechanisms.
Features
- CSS Property Suggestions: Analyzes UI task descriptions and suggests relevant CSS properties from MDN documentation
- Browser Support Checking: Provides detailed browser compatibility information for CSS properties
- User Consent Mechanism: Asks for user approval before recommending CSS properties with browser support information
- Implementation Guidance: Provides code examples, best practices, and fallback strategies
- MDN Integration: Fetches information from Mozilla Developer Network for accurate CSS documentation
Installation
pnpm install
pnpm run build
Usage
Add to your MCP settings:
{
"mcpServers": {
"mcp-css-first": {
"command": "node",
"args": ["dist/cli.js"]
}
}
}
Available Tools
1. suggest_css_solution
Suggests CSS-first solutions for UI implementation tasks by searching MDN documentation.
Parameters:
task_description(string): Description of the UI task or problem to solvepreferred_approach(optional): 'modern', 'compatible', or 'progressive'target_browsers(optional): Array of target browsers/versions
Example:
{
"task_description": "I need to center a div horizontally and vertically",
"preferred_approach": "modern"
}
2. check_css_browser_support
Checks browser support for specific CSS properties using MDN data.
Parameters:
css_property(string): CSS property name to checkinclude_experimental(optional boolean): Include experimental features
Example:
{
"css_property": "flexbox",
"include_experimental": false
}
3. get_css_property_details
Retrieves comprehensive information about a CSS property from MDN documentation.
Parameters:
css_property(string): CSS property name to get details forinclude_examples(optional boolean): Include code examples
Example:
{
"css_property": "grid",
"include_examples": true
}
4. confirm_css_property_usage
Confirms user consent for using a specific CSS property and provides implementation guidance.
Parameters:
css_property(string): CSS property name user wants to useuser_consent(boolean): User consent to use this CSS propertyfallback_needed(optional boolean): Whether fallback solutions are needed
Example:
{
"css_property": "container-queries",
"user_consent": true,
"fallback_needed": true
}
How It Works
- Task Analysis: When you describe a UI task, the server extracts relevant CSS keywords
- MDN Integration: Searches MDN documentation for appropriate CSS properties
- Browser Support: Provides detailed browser compatibility information
- User Consent: Asks for approval before recommending properties with support details
- Implementation: Provides code examples, best practices, and fallback strategies
Development
# Install dependencies
pnpm install
# Build for development
pnpm run build:tsc
# Watch for changes
pnpm run dev
# Build for production
pnpm run build
# Run tests
pnpm test
# Lint code
pnpm run lint
Project Structure
src/
├── index.ts # Main MCP server implementation
├── services/
│ └── mdnApi.ts # MDN API integration and CSS property logic
└── utils/
└── tryCatch.ts # Error handling utilities
CSS Property Coverage
The server currently supports suggestions for:
- Layout: Flexbox, Grid, positioning
- Responsive Design: Container queries, media queries
- Animations: CSS animations, transitions
- Visual Effects: Shadows, gradients, borders
- Typography: Font properties, text alignment
- Colors: Color properties, backgrounds
Browser Support Levels
- Excellent (95%+): Safe for production use
- Good (85%+): Consider fallbacks for legacy browsers
- Moderate (70%+): Use with caution and provide fallbacks
- Limited (<70%): Consider alternative approaches
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.
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.