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 system contracts, docs search, and usage validation for @digitaltableteur components.
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 …”。
适用于网页版、桌面版和手机版 Claude:
https://www.digitaltableteur.com/mcp在终端中运行这条命令
claude mcp add --transport http digitaltableteur https://www.digitaltableteur.com/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"digitaltableteur": {
"url": "https://www.digitaltableteur.com/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": {
"digitaltableteur": {
"type": "http",
"url": "https://www.digitaltableteur.com/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。
ChatGPT 只能连接互联网上的服务器:
https://www.digitaltableteur.com/mcp菜单名称可能因套餐和版本不同而略有差异。
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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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6日
注册名称已通过域名 digitaltableteur.com 验证(注册中心会核实域名所有权)
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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(2.0.0)于42天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
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。
_____ _______
| \ | | | | | | | | | | | | | | | || | | | |_____/ |_|
"Iteration beats perfection—ship today, learn tomorrow, refine forever."
Digitaltableteur is a hybrid monorepo portfolio website featuring both Next.js 16 (production) and Vite (legacy) applications. Built with React 19 and TypeScript 6.x, it showcases a comprehensive design system, multi-language support (EN/FI/SV), AI-powered chat interface, and enterprise-grade tooling including Sentry observability, Linear issue management, and MCP (Model Context Protocol) integrations.
# Clone repository
git clone https://github.com/PetriLahdelma/digitaltableteur.git cd digitaltableteur
npm install
cp .env.example .env.local
Required for development:
# Analytics
VITE_GA_ID=G-XXXXXXXXXX # Google Analytics 4
VITE_EMAILJS_SERVICE_ID=service_xxx VITE_EMAILJS_TEMPLATE_ID=template_xxx VITE_EMAILJS_PUBLIC_KEY=xxx
FIGMA_TOKEN=figd_xxx # Figma design access GITHUB_MCP_PAT=github_pat_xxx # GitHub operations CONTEXT7_API_KEY=xxx # Context7 documentation access
LINEAR_API_KEY=lin_api_xxx LINEAR_TEAM_ID=xxx LINEAR_PROJECT_ID=xxx
AKAUNTING_API_USERNAME=admin@digitaltableteur.com AKAUNTING_API_PASSWORD=xxx AKAUNTING_COMPANY_ID=1
Production only:
CV_PASSWORD=xxx # Secure resume download
OPENAI_API_KEY=sk-xxx # AI chat functionality SENTRY_DSN=https://xxx@xxx.ingest.sentry.io/xxx SENTRY_AUTH_TOKEN=xxx # Source map upload
See .env.example for complete list with descriptions.
# Next.js dev server (production app)
npm run dev # http://localhost:3001
npm run storybook # http://localhost:6010
# Type checking
npm run typecheck # TypeScript validation across project
npm run lint # ESLint + Stylelint npm run lint:fix # Auto-fix linting issues
npm test # Run all tests (Vitest) npm run test:watch # Watch mode npm run test:coverage # Coverage report (>80% target) npm run test:a11y # Accessibility tests (axe-core) npm run test:visual # Visual regression (Playwright + Storybook)
npm run typecheck && npm run lint && npm test && npm run build
# GitHub MCP Server
npm run github:mcp:test # Test connectivity and authentication
npm run figma:mcp:test # Test connectivity and authentication
npm run context7:mcp # Launch locally (respects CONTEXT7_API_KEY) npm run context7:mcp -- --remote-check # Test remote endpoint
npm run ts:mcp:status # Validate TypeScript language server npm run ts:mcp:status:stub # Generate stub status
npx tsx scripts/linear/create-issue.ts # Interactive issue creation npx tsx scripts/linear/update-issue.ts --issue DIG-16 --state "Done" npx tsx scripts/linear/check-issue.ts DIG-16 # Display issue details
node scripts/sentry-mcp.js issues digitaltableteur 10 --unresolved npm run generate-sentry-summary # Generate dashboard data
# Next.js production build
npm run build # Output: .next/
npm run build-storybook # Output: storybook-static/
# Vite to GitHub Pages
npm run deploy # Build + gh-pages deployment
npm run deploy-with-storybook # Deploy with visual regression report
npm run cache-bust # Add version metadata + .nojekyll
vercel --prod
Hybrid Deployment Strategy:
https://digitaltableteur.com)https://nextjs-app.vercel.app)/api/* routes)vercel.json)Vite Build:
Next.js Build:
The project uses a hierarchical CLAUDE.md/AGENTS.md system optimized for AI assistants:
Root Documentation (Universal Rules)
├── CLAUDE.md (380 lines) # Comprehensive authority for Claude Code ├── AGENTS.md (150 lines) # Quick reference for generic agents └── .github/copilot-instructions.md # GitHub Copilot specific
Subdirectory Documentation (Specific Context) ├── app/CLAUDE.md + AGENTS.md # Next.js App Router patterns ├── shared/components/CLAUDE.md + AGENTS.md # Component library rules ├── docs/AGENTS.md # Documentation navigation └── scripts/AGENTS.md # Automation patterns
Claude Code Configuration ├── .claude/settings.json # Hooks (auto-format, safety checks) └── .claude/commands/ # Custom slash commands ├── review.md # Comprehensive code review ├── fix-issue.md # GitHub issue workflow ├── create-component.md # Component generation └── create-linear-issue.md # Issue creation
CLAUDE.md (Claude Code Authority)
AGENTS.md (Generic AI Quick Reference)
Claude Code Enhancements
/review, /fix-issue, /create-component, /create-linear-issueClaude Code (automatic):
/review # Comprehensive code review
/fix-issue 123 # Analyze and fix GitHub issue /create-component Button # Generate component (5 files) /create-linear-issue Implement X # Create Linear issue
Generic AI Agents (manual reference):
cat AGENTS.md # Root rules
cat app/AGENTS.md # Next.js patterns cat shared/components/AGENTS.md # Component rules
Documentation:
If you need the raw design data, you can download the Figma file as JSON. Set the FIGMA_TOKEN environment variable with your personal access token, then run:
npm run fetch-figma
Synchronizes design tokens and assets from Figma using the API. The file is saved as figma.json in the project root.
npm run generate:sitemap # Generate XML sitemap
npm run generate:llms # Create LLM-friendly content index npm run generate:alt-text # Generate accessibility descriptions (requires OPENAI_API_KEY)
generate:alt-text streams local image bytes to the OpenAI Vision API so it can describe the actual artwork; add OPENAI_API_KEY (and optionally OPENAI_ALT_MODEL) to .env.local before running, or append --force to regenerate every alt attribute.
Quick Publish Workflow:
# Publish single article from Sanity
npm run sanity:publish-single
npm run sanity:publish
docs/SANITY_PUBLISHING_AUTOMATION.md for the complete automated publishing workflowdocs/SANITY_MIGRATION.md for the full migration workflow (React → Sanity via sanity:parse-posts / sanity:convert / sanity:upload, Sanity → MDX via sanity:sync-from-remote, redirects generation, cleanup helpers)digitaltableteur/
├── app/ # Next.js 16 App Router (production) │ ├── layout.tsx # Root layout with providers │ ├── page.tsx # Home page (server component) │ ├── about/page.tsx # Route pages │ ├── blog/[slug]/page.tsx # Dynamic routes │ └── api/*/route.ts # API routes (Vercel functions) │ ├── src/
只显示了开头部分;其余内容请在仓库中阅读