No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by jonthebeef · MCP Server · ★ 77
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is superdesign-mcp-claude-code safe to install? View the security audit →
Superdesign MCP Server An MCP (Model Context Protocol) server that brings Superdesign - an open source AI design agent by @jasonzhou1993 and @jackjacketh - to Claude Code as native tools. This server operates as a "design orchestrator" that provides structured specifications for your IDE's LLM to execute, enabling Superdesign's sophisticated design capabilities without requiring Anthropic API keys. Key Benefits No API Keys Required: Works directly with Claude Code's built-in LLM connection Local Execution: Runs entirely on your machine as an MCP server IDE Integration: Seamlessly integrates with Claude Code (and potentially Cursor, Windsurf, or other MCP-compatible IDEs - untested) Based on Open Source: Built on top of Superdesign.dev, an open source AI design system Installation Install dependencies: Build the server: Claude Code Integration Add the MCP server to your Claude Code configuration: Example : json { "mcpServers": { "superdesign": { "command": "node",
| Stars | 77 |
| Forks | 12 |
| Language | HTML |
| Category | MCP Server |
| Quality Score | 59.3032576359786/100 |
| Last Updated | 2026-03-10 |
| Created | 2025-07-08 |
| Platforms | claude-code, mcp |
| Est. Tokens | ~811k |
These tools work well together with superdesign-mcp-claude-code for enhanced workflows:
Explore other popular mcp server tools:
superdesign-mcp-claude-code is an open-source mcp server by jonthebeef with 77 GitHub stars.
superdesign-mcp-claude-code is primarily written in HTML.
You can find installation instructions and usage details in the superdesign-mcp-claude-code GitHub repository at github.com/jonthebeef/superdesign-mcp-claude-code. The project has 77 stars and 12 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: