Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
作者提供的说明(英文原文)
Design tokens from any live site: colours, type, spacing, components, drift against a baseline.
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": {
"dembrandt": {
"command": "npx",
"args": [
"-y",
"dembrandt",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add dembrandt -- npx -y dembrandt mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"dembrandt": {
"command": "npx",
"args": [
"-y",
"dembrandt",
"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": {
"dembrandt": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"dembrandt",
"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 dembrandt 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(0.39.2)于26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:Figma Context MCP, Claude Real Video, Figma MCP Server
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
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
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。
Extract any website's design system in one command. Enforce it in CI.
Logo, colors, typography, spacing, borders, shadows, motion, components. W3C design tokens in seconds.
npm install -g dembrandt
dembrandt install-browser # one-time: fetches the matching Chromium dembrandt dembrandt.com
The browser step is required. dembrandt drives Chromium through playwright-core, which ships no browser binaries, so a fresh install has nothing to launch until you run it. Skipping it fails with browser engine not available.
Or use npx without installing: npx dembrandt dembrandt.com. The browser step applies here too: run npx dembrandt install-browser first. Browsers land in a shared Playwright cache, so either route only needs it once.
Requires Node.js 18+
Or install the MCP server straight into your editor and let the agent run it:
Playwright renders the page, dembrandt reads computed styles from the DOM, analyzes color usage and confidence, groups similar typography, detects spacing patterns, and returns design tokens.
dembrandt dembrandt.com --shadcn # shadcn/ui theme, observed slots only
dembrandt dembrandt.com --dtcg # W3C design tokens, for Style Dictionary or Tokens Studio dembrandt dembrandt.com --wcag # WCAG 2.1 contrast on real DOM pairs
Default is formatted terminal output only. Every flag below; the detailed reference is [docs/usage.md](docs/usage.md).
Export
| Flag | What you get |
|---|---|
--dtcg | W3C design tokens (DTCG) |
--design-md | DESIGN.md for AI agents |
--tailwind [path] | Tailwind v4 @theme CSS |
--shadcn [path] | shadcn/ui theme, observed slots only |
--html [path] | Self-contained HTML report |
--brand-guide | Brand guide PDF |
--json-only | Raw JSON to stdout |
--save-output | JSON to output/ / |
--screenshot | Viewport screenshot |
--color-format | Colour notation: hex, rgb, oklch, lch, source |
--raw-colors | Pre-filter colours too |
Analysis
| Flag | What you get |
|---|---|
--wcag | Contrast grades on real DOM pairs |
--compare | Drift gate; exits 1 when tokens moved |
--tokens | Check rendered colours, radii and font sizes against a W3C Design Tokens file; repeat for several |
--max-off-token | With --tokens: exit 1 when more than N rendered values match no token |
--tokens-report | With --tokens: Markdown summary with the nearest token per off-token value, wiki-ready |
--annotations | CI annotations for drift and off-token values; detected from the runner by default |
--approve | Accept the current run as the new baseline |
--ai | ML brand-primary prediction (experimental) |
Coverage
| Flag | What you get |
|---|---|
--crawl [n] | Merge N pages, cross-page confidence |
--sitemap | Discover pages from sitemap.xml |
--dark-mode | The dark theme's tokens |
--mobile | Mobile viewport |
--slow | 3x timeouts for heavy sites |
--browser | chromium or firefox; CDP via env |
--no-sandbox | For Docker and CI |
Access
| Flag | What you get |
|---|---|
--cookie | Reach pages behind a session |
--cookie-file | JSON cookies, Playwright storageState (incl. localStorage and the sessionStorage block --save-storage-state adds), or Netscape cookies.txt |
--basic-auth | HTTP Basic for the browser context |
--login | Open a visible browser to sign in; press Enter when ready, then extract (interactive terminal only) |
--save-storage-state | With --login, save the signed-in session (cookies, localStorage, sessionStorage) to a file; reuse it later with --cookie-file, also in CI |
--header | Any extra request header, repeat for several |
--no-headed-fallback | Never open a visible browser on a failed navigation; for batch runs |
--user-agent | Custom user agent |
--locale | Locale for the fingerprint |
--timezone | Timezone for the fingerprint |
--accept-language | Accept-Language header |
--screen-size | Reported screen resolution |
--stealth | Anti-detection; authorized use only |
--key | Sync runs to your account |
Extract a preview deployment, compare against a committed baseline, fail the job when tokens moved:
- uses: dembrandt/dembrandt@v0.39.2
with: url: https://preview.example.com baseline: .dembrandt/baseline.json
The action is on the GitHub Marketplace and annotates the PR with the drifted tokens. On any other runner the gate is just an exit code plus JSON: dembrandt URL --compare baseline.json --json-only exits 1 on drift and prints per-token changes[]. See [docs/ci.md](docs/ci.md) for the Action inputs, the platform-neutral gate, and the exit code table.
Copy a command, paste a prompt, get a result. Competitor benchmarking, WCAG audits, Figma token push, agentic design system builds. Filterable by role at [dembrandt.com/recipes](https://www.dembrandt.com/recipes), with the basics in docs/recipes.md.
Use Dembrandt as a tool in Claude Code, Cursor, Windsurf, or any MCP-compatible client. Ask your agent to "extract the color palette from dembrandt.com" and it calls Dembrandt automatically.
Per-client setup, environment variables and the full tool list: [docs/mcp.md](docs/mcp.md) and [dembrandt.com/mcp](https://www.dembrandt.com/mcp).
claude mcp add --transport stdio dembrandt -- npx -y dembrandt mcp
The server is listed in the MCP Registry as io.github.dembrandt/dembrandt, so a client that reads the registry can install it by name.
Or add to your project's .mcp.json:
{
"mcpServers": { "dembrandt": { "command": "npx", "args": ["-y", "dembrandt", "mcp"] } } }
Available tools include get_design_tokens, get_color_palette, get_typography, get_component_styles, get_surfaces, get_spacing, and get_brand_identity, plus pure analysis tools (compute_drift, get_findings, export_dtcg, generate_design_md, render_report) and job-control tools.
Extraction tools accept slow, mobile, darkMode, wcag, cookie, cookieFile, basicAuth and header (for authenticated pages), userAgent, and noSandbox (Docker and most CI containers). Interactive --login stays CLI-only. Set pages above 1 to crawl and merge several pages, which produces a markedly stronger token set than one page; paths names them explicitly and sitemap discovers them from sitemap.xml.
Extraction returns a job_id. Poll it with get_job_status, then hand that same id to the pure tools instead of passing the extraction back as an argument:
get_design_tokens(url: "example.com", pages: 5) -> job_id
get_job_status(job_id) -> tokens get_findings(job_id) -> contrast and consistency issues export_dtcg(job_id) -> W3C design tokens
Pair with [dembrandt-skills](https://github.com/dembrandt/dembrandt-skills) to give your agent UX intelligence on top of extracted tokens: hierarchy, accessibility, interaction states, and a full 6-stage design pipeline orchestrator.
npx skills add dembrandt/dembrandt-skills
Load extractions, track token drift, and compare snapshots. [dembrandt.com/app](https://www.dembrandt.com/app)
--key to the CLI. Every run uploads a snapshot to your account and scores it against the previous one for that domain. Wire into GitHub Actions or any CI runner and every deploy records itself.--dark-mode flag (not automatically detected)--mobile for 390x844 mobile viewport)Dembrandt reads publicly available CSS and computed styles from website DOMs for documentation, learning, and analysis of design systems you own or have permission to analyze.
Only run Dembrandt against sites whose Terms of Service permit automated access, or against your own properties. Do not use extracted material to reproduce third-party brand identities, logos, or trademarks. Respect robots.txt, rate limits, and copyright.
Dembrandt d
只显示了开头部分;其余内容请在仓库中阅读