by Manavarya09 · MCP Server · ★ 4.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is design-extract safe to install? View the security audit →
Featured in: AI Design Tools
| Stars | 4,758 |
| Forks | 399 |
| Language | HTML |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72/100 |
| Open Issues | 18 |
| Last Updated | 2026-11-05 |
| Created | 2026-04-15 |
| Platforms | browser, claude-code, cli, mcp |
| Est. Tokens | ~19k |
DESIGNLANG Reverse-engineer any website's complete design system in one command. designlang crawls any website with a headless browser, extracts every computed style from the live DOM, and generates 8 output files — including an AI-optimized markdown file, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS custom properties.
These tools work well together with design-extract for enhanced workflows:
Looking for a design-extract alternative? If you're comparing design-extract with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Extract any website’s design system into tokens in seconds: logo, colors, typography, borders & more. One comm
Turn Claude into a senior design architect: DTCG tokens, 52 components, WCAG 2.2 AA-AAA, 138 design systems, a
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici
Reverse engineer any website into a typed API client. Works with Claude Code, Codex, Cursor and OpenCode.
Open-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows f
MCP server to provide Figma layout information to AI coding agents like Cursor
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: