MCP Catalogs
Homemcp-design-system-extractor screenshot

mcp-design-system-extractor

by freema·64·Score 46

MCP server that extracts HTML, styles and component metadata from Storybook design systems to help with development.

developer-toolsai-llmweb-scraping
12
Forks
0
Open issues
3 mo ago
Last commit
2d ago
Indexed

Overview

The MCP Design System Extractor connects to Storybook instances to extract component information, rendered HTML, styles, and design tokens. It uses Puppeteer with headless Chrome for dynamic JavaScript rendering and provides both synchronous and asynchronous modes for component extraction. The server features a job queue system for long-running operations with concurrent processing capabilities. It supports comprehensive design system analysis including theme extraction, component dependency analysis, and CSS token extraction.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Help developers extract HTML and styles from Storybook components to recreate them in other frameworks
you:Analyze design system components to identify patterns and dependencies for new feature development
you:Extract design tokens and theme information to ensure consistent styling across applications
you:Does it work with all versions of Storybook?
you:What if my component takes a long time to render?

When to choose this

Choose this MCP server when working with Storybook-based design systems and need AI assistance to analyze, extract, or reproduce component implementations.

When NOT to choose this

Don't use this if your Storybook instance requires authentication beyond basic URL access or if you need to extract information from non-Storybook design systems.

Tools this server exposes

9 tools extracted from the README
  • list_components

    Lists all available components from the Storybook instance

  • get_component_html

    Extracts HTML from a specific component story

  • search_components

    Search components by name, title, category, or purpose

  • get_component_dependencies

    Analyzes rendered HTML to find which other components are used internally

  • get_theme_info

    Extracts design system theme (colors, spacing, typography, breakpoints)

  • get_external_css

    Extracts and categorizes CSS tokens from external CSS files

  • job_status

    Check status of an async job

  • job_cancel

    Cancel a queued or running job

  • job_list

    List all jobs with their status

Comparable tools

storybook-mcpdesign-token-extractorcomponent-analyzer

Installation

Using Claude CLI (Recommended)

claude mcp add design-system npx mcp-design-system-extractor@latest \
  --env STORYBOOK_URL=http://localhost:6006

Using npm

npm install -g mcp-design-system-extractor

Configuration

Add to Claude Desktop config.json:

{
  "mcpServers": {
    "design-system": {
      "command": "node",
      "args": ["/path/to/dist/index.js"],
      "env": {
        "STORYBOOK_URL": "http://localhost:6006"
      }
    }
  }
}

FAQ

Does it work with all versions of Storybook?
It works with built Storybook distributions that expose the standard `/index.json` and `/iframe.html` endpoints. The most recent versions are supported.
What if my component takes a long time to render?
The server uses asynchronous job processing by default for long-running operations. You can poll job status to track completion without timeout errors.

Compare mcp-design-system-extractor with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.