经 AI Skill Hub 精选评估,Figma MCP工具 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Figma MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Figma MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/slashdoodleart/figma-mcp-free
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"figma-mcp--": {
"command": "npx",
"args": ["-y", "figma-mcp-free"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Figma MCP工具 执行以下任务... Claude: [自动调用 Figma MCP工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"figma_mcp__": {
"command": "npx",
"args": ["-y", "figma-mcp-free"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<br/>
A plugin + MCP server that streams live Figma document data to AI coding tools without hitting Figma's REST API rate limits. Figma's free-tier API limits are brutal (a handful of requests per month), so I built this to bypass that entirely — the plugin reads directly from the Figma canvas and streams data over a local WebSocket to the MCP server.
get_design_context and get_screenshot accept nodeIds to target specific nodes without selecting them in Figmacd server && npm install && npm run build
cd ../plugin && npm install && npm run build ```
Then run ./install.sh (or .\install.ps1) to configure your AI tools.
| Tool | Config file |
|---|---|
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Linux) | ~/.config/claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Claude Code | ~/.claude/mcp.json |
| Cursor | ~/.cursor/mcp.json |
| VS Code / GitHub Copilot | ~/Library/Application Support/Code/User/mcp.json (macOS) |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Gemini Code (Antigravity) | ~/Library/Application Support/Google/GeminiCode/mcp_config.json |
| Zed | ~/.config/zed/settings.json |
Add the MCP server entry to mcpServers in the relevant file:
{
"mcpServers": {
"figma-mcp-free": {
"command": "node",
"args": ["/absolute/path/to/figma-mcp-free/server/dist/index.js"]
}
}
}
Or use npx (no build required):
{
"mcpServers": {
"figma-mcp-free": {
"command": "npx",
"args": ["-y", "figma-mcp-free"]
}
}
}
Runs inside Figma and reads directly from the canvas using the Figma Plugin API. It serializes nodes into structured JSON with full layout, typography, visual styles, design tokens, and component data. Connects to the MCP server over WebSocket at ws://localhost:1994.
Add to ~/Library/Application Support/Code/User/mcp.json (global) or .vscode/mcp.json (workspace):
{
"servers": {
"figma-bridge": {
"type": "stdio",
"command": "npx",
"args": ["-y", "figma-mcp-free"]
}
}
}
For the best experience, use the included VS Code agent (Figma MCP Free) and Copilot instructions in .github/copilot-instructions.md — they define the recommended design-to-code workflow.
高质量开源MCP工具,提升设计开发效率
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Figma MCP工具 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | figma-mcp-free |
| 原始描述 | 开源MCP工具:MCP server + Figma plugin that streams live design data to AI coding tools — no 。⭐7 · TypeScript |
| Topics | figmamcptypescript |
| GitHub | https://github.com/slashdoodleart/figma-mcp-free |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-01 · 更新时间:2026-06-01 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端