Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Finds UI drift in React apps (buttons, cards, colors, spacing) and gives your agent each fix
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tavero": {
"command": "npx",
"args": [
"-y",
"tavero",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add tavero -- npx -y tavero mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"tavero": {
"command": "npx",
"args": [
"-y",
"tavero",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tavero": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tavero",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 baccaraaa 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.7.0)于13天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, First Sale Scout
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Playbooks and a 14-day checklist for founders winning their first paying customers.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Tavero
Keep the UI your agent writes consistent.
taveroui.com · Docs · Demo
Tavero scans your running React app, finds drift in buttons, cards, colors and spacing, and gives your coding agent each fix with the file, the line and the token to use. It runs on your machine, as a CLI, an MCP server for Claude Code, Cursor, Codex and other agents, and a local panel where you decide what is intended.
A real finding from the Acme demo in this repository (demo/acme): six pages scanned at three widths.
Node 20 or later, a Vite or Next app on React 19 that runs in dev mode.
npm i -D tavero
npx playwright install chromium # once per machine npx tavero login --url http://localhost:5173/login # once, if the app has a login npx tavero scan --url http://localhost:5173 npx tavero findings
id sev rule decision title evidence f_c75ac3d6a2 high buttons 7 text button styles 7 f_36cb934b5e high scales 13 distinct padding values, 1 declared 12 f_94269275c1 medium buttons Two text button styles differ only in radius, paddingY, pa… 2 f_057122e1f9 medium buttons 4 place(s) write directly in page or section mark… 4 … 30 more, use --page 2
npx tavero finding f_ff30adc07c # evidence: file:line, current value, expected token, crops
npx tavero context # a ~1,500-token brief of the design system for an agent npx tavero report # a self-contained HTML report
Tavero writes only to /.tavero/. Every read command takes --json, and text output is capped at 20 rows so it fits an agent's context.
tavero mcp is an MCP server on stdio with nine tools. Print the config for your client and paste it where it says:
npx tavero mcp --print-config claude # Claude Code: .mcp.json
npx tavero mcp --print-config cursor # .cursor/mcp.json npx tavero mcp --print-config codex # .codex/config.toml npx tavero mcp --print-config gemini # .gemini/settings.json npx tavero mcp --print-config antigravity # .agents/mcp_config.json npx tavero mcp --print-config vscode # .vscode/mcp.json (GitHub Copilot) npx tavero mcp --print-config windsurf # ~/.codeium/windsurf/mcp_config.json
Then paste docs/AGENTS.snippet.md into AGENTS.md, CLAUDE.md or GEMINI.md, so the agent reads the design context before writing UI. SKILL.md is an Agent Skill with the full workflow.
A recorded run of Claude Code on the Acme demo, with no shell, 29 seconds:
› tavero_context
Action button is Button from src/components/Button.tsx (props: variant) › tavero_findings rule=colors f_ff30adc07c Color #4263eb is not a project token › tavero_finding f_ff30adc07c src/app.css:33 literal #4263eb in source expected --acme-primary #3b5bdb (ΔE 3.5) edit src/app.css:33 background: #4263eb → var(--acme-primary) › tavero_scan routes=/billing rules=colors › tavero_diff resolved f_ff30adc07c Color #4263eb is not a project token resolved f_18862a0332 Hardcoded color #4263eb in 1 place(s) new 0
| Tool | Use |
|---|---|
tavero_context | design-system brief; call before writing UI |
tavero_findings, tavero_finding | problems, worst first; one problem with evidence, the expected value and the exact rescan call |
tavero_scan | scan the app; after a fix, only the touched routes and rules. Streams progress, cancellable |
tavero_diff | resolved, new and unchanged findings since the previous scan |
tavero_components, tavero_component, tavero_show, tavero_tokens | inventory, crop paths, tokens |
| Rule | Reports |
|---|---|
buttons | distinct text and icon button styles with the components that render them, near-duplicate pairs, s written outside button components |
cards *(preliminary)* | distinct card styles, near pairs, card-like containers built inline |
colors | colors outside your tokens with the nearest token and ΔE, Tailwind default colors in a project with its own palette, near-identical pairs, hardcoded literals with file and line; in a dark theme, backgrounds that stay light, dark text on a dark page and dark-only colors without a token |
scales | radius, padding, gap, font size, weight and shadow values off the scale your tokens declare |
npx tavero ui --open # http://127.0.0.1:4747
A local panel for the person behind the agent. Go through the findings with the keyboard and decide. The agent sees each decision on its next call, without a rescan.
| Decision | What the agent sees |
|---|---|
| Fix | the finding comes first, marked as confirmed work |
| Intended | hidden until the finding gains new places |
| Canonical | on button and card variants: the reference variant and allowed ones, optionally named ("primary", "ghost"); the others get it as expected |
| Note | a message delivered with the finding |
Decisions are stored in .tavero/decisions.json, keyed by stable finding ids. Commit it to share them with your team and its agents. npx tavero ui --export ./panel writes a static, read-only copy of the panel.
cards rule is marked preliminary.npm ci
npx playwright install chromium npm test # unit and Playwright runtime tests; starts the test apps itself npm run typecheck npm run build
The website lives in site/ (Next.js static export). npm run site:install && npm run site:dev runs it; npm run site:audit runs its gates: Tavero on the site itself with 0 high and medium findings, Lighthouse, axe and three widths.
src/
core/ scan orchestration, aggregates, query API, decisions, diff, stable ids project/ framework detection static/ tokens, Tailwind theme and palette, hardcoded colors, component index runtime/ dev server, session, crawl, in-page collector, attribution, crops rules/ signatures and the four rules context/ the agent-facing brief report/ HTML report mcp/ MCP server, tools, client configs ui/ local panel and static export cli/ the command line demo/acme/ a small dashboard with deliberate drift, used by tests and the website test/ unit and runtime tests with mini Vite and Next apps design/ design tokens shared by the panel and the website site/ the website
See CONTRIBUTING.md before opening a pull request.