better-design: Open-source design MCP server + shadcn/ui registry — AI design systems for Claude Code, Cursor, Codex, GitHub

by marvkr · MCP Server · ★ 532

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: AI Design Tools

How to install better-design

npx shadcn@latest add https://www.better-design.com/registry/<design-system>/<component>.json
npx shadcn@latest add https://www.better-design.com/registry/linear/button.json

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 70/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

ai-designclaude-codeclaude-code-for-designclaude-designcodex-designcoding-agentscomponent-librarycursorcursor-designdesign-systems

Quick Facts

Stars532
Forks30
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score70/100
Open Issues1
Last Updated2026-10-25
Created2026-05-05
Platformsclaude-code, cli, codex, mcp, node
Est. Tokens~17k

About better-design

Better Design: Open source Claude Design Turn your AI coding IDE into a design engineer. Better Design works with MCP-compatible agents and editors like Claude Code, Cursor, VS Code/GitHub Copilot, Claude Desktop, and claude.ai. It is a design MCP server, AI design-system registry, and UI review layer for generating polished product interfaces from prompts.

Compatible Skills

These tools work well together with better-design for enhanced workflows:

  • styleseed — semantic(0.67)+complementary+shared_fw(vercel)+rare_topics+same_lang+similar_pop+shared_platform (97%)
  • open-design — semantic(0.57)+complementary+shared_fw(vercel)+rare_topics+same_lang+shared_platform (78%)
  • open-codesign — semantic(0.38)+complementary+shared_fw(vercel)+rare_topics+same_lang+shared_platform (70%)
  • shieldcn — semantic(0.21)+complementary+shared_fw(vercel)+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • typeui — semantic(0.43)+complementary+rare_topics+same_lang+similar_pop+shared_platform (69%)

better-design alternative? Top 6 similar tools

Looking for a better-design alternative? If you're comparing better-design 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.

  • styleseed by bitjaru · ⭐ 1.0k

    Open-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows f

  • ccmanager by kbwo · ⭐ 1.3k

    Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI

  • Claude-Skills by borghei · ⭐ 971

    385 AI skills, 76 expert agents, and 906 stdlib Python tools for every team: engineering, PM, marketing, C-lev

  • memorix by AVIDS2 · ⭐ 903

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • vibe by mondaycom · ⭐ 693

    🎨 Vibe Design System - Official monday.com UI resources for application development in React.js

  • awesome-vibe-coding-guide by analyticalrohit · ⭐ 379

    Become 10x Vibe Coder. Awesome Vibe Coding guide, best practices, and tips for efficient and controlled AI ass

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools