Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
grab/cursor-talk-to-figma-mcp
让AI编程助手直接读取和修改Figma设计稿的MCP插件。For Cursor, Claude Code, or Codex users: a connection that lets the AI inspect and modify Figma designs programmatically.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
让 Cursor 读懂 Figma 设计稿
用 Cursor 修改 Figma 里的元素
新建 Figma 中的图形与文字
调整元素排版、间距与样式
Read the current Figma page and selected layers.
Change text content, auto layout, and spacing.
Create new elements and connect prototype interactions.
Apply styles and organize components and layers.
Export assets and inspect document structure.
上手GET STARTED
curl -fsSL https://bun.sh/install | bash选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl -fsSL https://bun.sh/install | bash
静态扫描发现高风险:安装文档要求通过 curl 直接执行远程脚本(curl -fsSL https://bun.sh/install | bash),存在供应链风险。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。The static scan flagged a high-risk install step: the docs tell you to run `curl -fsSL https://bun.sh/install | bash`, piping a remote script straight into your shell. Inspect that script before you run it.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+1.1%+1.1%
7.0k → 7.1k stars · 49 个快照7.0k → 7.1k stars · 49 snapshots
状态STATUS
长期未更新Not updated
质量 B+Quality B+
GitHub 上已有 7050 颗星和 779 个 fork,说明有不少人关注或试用。Created in March 2025
依赖:Dependencies:@modelcontextprotocol/sdk, uuid, ws, zod
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …ion between AI agent (Cursor, Claude Code) and Figma, allowing AI agent…"
},
{
"agent": "cursor",
"evidence": "readme: …ursor MCP configuration in `~/.cursor/mcp.json`: ```json { \"mcpServers\":…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 9,
"ai-tools": 12,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 11,
"productivity": 3
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": null,
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 5,
"media": 1,
"design": 15,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "smithery.yaml",
"weight": 0.85
},
{
"signal": "package.json depends on @modelcontextprotocol/sdk + MCP framing",
"weight": 0.8
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": ".mcp.json (configures servers it uses)",
"weight": 0.3
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}