Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
MCPpedia last refreshed this data
io.github.gregkozakiewicz/roast-my-design-system is an MCP server that audit your Design System and serve your Agent the rules that keep AI-written UI on-system. Its tool list has not been published yet over stdio and sse, requires no API key, and scores 64/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-gregkozakiewicz-roast-my-design-system": {
"args": [
"-y",
"roast-my-design-system"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A free CLI tool (and Claude Code skill) that roasts your repo's design system with real data, then generates the rules that keep your AI agent on-system.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'roast-my-design-system' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked roast-my-design-system against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in design
AI-native design editor. Open-source Figma alternative.
AI image generation and editing with prompt optimization and quality presets. Powered by Nano Banana
Draw and visually collaborate with your agents on tldraw's canvas.
3D & AR SDK for Android, iOS, Web — API docs, samples, validation, and code generation.
MCP Security Weekly
Get CVE alerts and security updates for io.github.gregkozakiewicz/roast-my-design-system and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A free CLI tool (and Claude Code skill) that roasts your repo's design system with real data, then generates the rules that keep your AI agent on-system.
New in 5.1: the roast's analysis now ships inside the report. Run as the Claude Code skill, the report gains a "What the numbers mean" section — Claude's read of your scan, in the same shareable file as the score, so the analysis reaches whoever the report is forwarded to. Labelled as written by AI, never mixed into the measurement.
New in 5.0: it runs as a local MCP server. One command, and your agent asks the design system before writing UI, then gets the work checked after: which Button is canonical, which token holds that colour, review my changes. Local, deterministic, nothing leaves your machine. See Live answers over MCP.
Run it on your codebase and get, in about a second:
packages/ui scores 80 while apps/web scores 40, and now you can see it.design-system-rules.md with canonical components, your token file, and known duplicates to avoid, so your AI agent follows your system instead of guessing at it. --apply injects them into every agent file you have: Claude, Cursor, GitHub Copilot, and Windsurf. Every scan also checks the rules you already have for stale references: paths that no longer exist, components named canonical that nothing imports anymore.Your AI agent (Claude, Cursor, Copilot) builds UI by imitating what's already in your repo. If your repo has 112 colours and four Button implementations, your agent guesses which one is canonical, and it picks wrong half the time. That's why AI-generated UI looks almost-but-not-quite right. The first step to fixing it is seeing the mess measured.
One scan powers all of it; the flags decide what lands on disk. Combine freely.
| Command | What you get |
|---|---|
npx roast-my-design-system@latest</code |