
Figma MCP PRO
Professional Model Context Protocol server that enables AI-optimized Figma design analysis and comprehensive design-to-code conversion through a structured 5-step workflow.
README
Figma MCP PRO
Professional Model Context Protocol (MCP) server for AI-optimized Figma design analysis. Clean 5-step workflow for comprehensive design-to-code conversion with smart comment processing and asset downloads.
🚀 Key Features
- 5-Step Workflow: Framework selection → Design data → Comments → Assets → Reference analysis
- AI-Optimized: Structured data specifically formatted for AI code generation
- 10 Framework Support: React, Vue, Angular, Svelte, HTML/CSS/JS, SwiftUI, UIKit, Electron, Tauri, NW.js
- Smart Comments: Coordinate-based matching of designer comments to UI elements
- Asset Downloads: Batch download with original Figma export settings
- CSS Generation: Automatic CSS from Figma properties (padding, margins, borders, effects)
📦 Installation
npm install -g figma-mcp-pro
⚙️ Quick Setup
1. Get Your Figma API Key
Get your API token from Figma Account Settings → Personal access tokens
2. Copy & Paste MCP Configuration
📋 Use the copy button on the code block below, then replace your-api-key-here
with your actual API key:
{
"mcpServers": {
"Figma MCP PRO": {
"command": "npx",
"args": ["figma-mcp-pro@latest", "--figma-api-key", "your-api-key-here"],
"env": {
"DEBUG": "true"
}
}
}
}
Configuration File Locations:
- Claude Desktop:
claude_desktop_config.json
- Claude Code (VS Code): VS Code MCP settings
- Cursor, Windsurf, TRAE: Application MCP configuration settings
📝 Tool Reference
Core Tools
show_frameworks
Shows available frameworks. Call first to choose target framework.
get_figma_data
Extracts AI-optimized design data with framework-specific processing.
- Input: Figma URL + framework
- Output: Design structure, CSS properties, layout data
process_design_comments
Matches designer comments to design elements with AI implementation prompts.
- Input: Figma URL + framework
- Output: Comment-to-element mapping with actionable instructions
download_design_assets
Downloads export-ready assets with original Figma settings + reference image.
- Input: Figma URL + local path
- Output: Asset files + reference.png for visual context
check_reference
Analyzes reference.png for design understanding and development guidance.
- Input: Assets folder path + framework
- Output: Design analysis and framework-specific development recommendations
🎯 What You Get
Design Data
- Layout: Padding, margins, gaps, auto-layout properties
- Styling: Colors, borders, shadows, effects, typography
- Structure: Component hierarchy, semantic roles
- Responsive: Flexible sizing, constraints, breakpoints
Smart Comments
- Coordinate Matching: Comments linked to specific design elements
- AI Instructions: "Add hover animation to Button component"
- Implementation Context: Element details + positioning
Asset Downloads
- Export Settings: Respects Figma's configured export settings
- Original Names: Uses actual node names as filenames
- Visual Reference: reference.png shows complete design context
- Multiple Formats: SVG, PNG, JPG, PDF support
🌟 Framework Optimizations
- React: TypeScript, Hooks, Custom Hooks, Performance optimization
- Vue: Composition API, TypeScript, Pinia stores, Composables
- Angular: Standalone components, Signals, Modern templates, TypeScript
- Svelte: Svelte 5 runes, TypeScript, SvelteKit, Stores
- HTML/CSS/JS: Design tokens, Modern CSS, Accessibility-first
- SwiftUI: State management, MVVM, Accessibility, Modern patterns
- UIKit: Modern concurrency, SwiftUI interop, Auto Layout
- Electron: Security hardening, IPC patterns, Native integration
- Tauri: Rust commands, Event system, Security, WebView
- NW.js: Unified context, Node.js integration, Chromium APIs
📄 License
MIT License
🆘 Support
- Issues: GitHub Issues
- NPM: figma-mcp-pro
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。