设计资源DESIGN· INSPIRATION
qiuyiwu1989-star/opendesign
为AI编程代理提供真实网页设计规范的MCP服务,让生成界面有品味。OpenDesign gives AI coding agents access to 1,486 real web design systems as machine-readable tokens, so the UI they build looks good, not just works.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
提取任意网站的设计样式
为项目推荐风格相近的设计参考
获得真实产品验证过的设计token
自己运行脚本分析网站设计
让构建的软件拥有真实设计品味
Pull real design tokens from 1,400+ shipped websites
Get color, typography, spacing, and motion specs for any reference site
Compare multiple design systems to choose the right aesthetic
Use real-world design data directly in your AI coding tool
Extract design tokens from your own site with the open-source extractor
上手GET STARTED
{ "mcpServers": { "opendesign": { "url": "https://opendesign.cc/mcp/http" } } }选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserreadme
Every entry is extracted by driving a real browser (Playwright), reading `getComputedStyle` off the actual DOM, aggregating by frequency, an
02控制浏览器Controls a browserskill.md
│ ├── 02_desktop_hero.png ← real Playwright screenshots (hero + scroll sections + mobile)
扫描发现中等风险:项目会控制浏览器(Playwright)来抓取真实网站的设计数据,这可能在运行时带来安全顾虑。未发现高风险项。The static scan flagged medium risk because OpenDesign uses Playwright to drive a real browser and take screenshots. This is expected for its extraction process, but review the code before running it on sensitive sites.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+1.4%+1.4%
73 → 74 stars · 49 个快照73 → 74 stars · 49 snapshots
状态STATUS
持续活跃Active
项目收录了1486个真实网页设计系统,可直接用于AI编码代理,提升生成界面的设计品味。1,486 real design systems, extracted from live websites via browser instrumentation
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …` Works with Claude Desktop, Claude Code, Cursor, Windsurf — any MCP c…"
},
{
"agent": "claude-desktop",
"evidence": "readme: …n-mcp\"] } } } ``` Works with Claude Desktop, Claude Code, Cursor, Windsur…"
},
{
"agent": "windsurf",
"evidence": "readme: …Desktop, Claude Code, Cursor, Windsurf — any MCP client. No account,…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 6,
"ai-tools": 7,
"dev-tools": 0,
"indie-web": 2,
"skill-agent": 13,
"productivity": 0
},
"primary": "ai-tools",
"secondary": "chat-agent"
},
"localRuntime": null,
"skillMdTotal": 2,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 6,
"browser": 4,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "2 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skill.md",
"skill/SKILL.md"
],
"skillMdFetched": 2
}