SKILLS & AGENTS/Skill 与 Agent·MCP-SERVER

figma-console-mcp

southleft/figma-console-mcp

给 AI 一个 Figma 控制台，自动提取样式、创建组件、排查视觉问题

让AI直接读写Figma设计，设计师可快速提取、创建和调试设计。Your design system as an API.

打开仓库Open repository 官网Homepage 上升中Rising

怎么装：Install: claude mcp add figma-console -s user -e FIGMA_ACCESS_TOKEN=figd_YOUR_TOKEN_HERE -e ENABLE_MCP_APPS=true -- npx -y figma-console-mcp@latest

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.1%+0.1%

2.4k → 2.4k stars · 3 个快照2.4k → 2.4k stars · 3 snapshots

状态STATUS

持续活跃Active

项目自2025年10月发布以来已获得2436个星标，社区关注度高。

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

01
用AI创建和修改Figma设计
02
提取设计文件中的颜色与变量
03
读取设计组件的详细属性
04
比对前端代码与设计的一致性

04 / 安装04 / Install

怎么装How to install

CLAUDE-MCP

$

README 里给出的安装方式。The installation method given in the README.

MCP CONFIG

$

MCP 客户端配置，粘贴到对应的配置文件里即可。An MCP client config — paste it into the relevant config file.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

推荐使用npx运行`npx -y figma-console-mcp@latest`，并设置环境变量`FIGMA_ACCESS_TOKEN`和`ENABLE_MCP_APPS=true`，具体配置见文档中claude mcp add或JSON示例。

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。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

需检查Needs review

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/southleft/figma-console-mcp
原始数据哈希Raw data hash: af52f5336051049503a97b97c6d36989
解析时间Parsed at: 2026-10-05T22:12:51.830Z
最后一次验证Last verified: 2026-10-05T13:45:39.240Z
增长测量时间Growth measured: 2026-10-05T22:16:26.213Z
发现查询Discovery queries: focus:design:repo:figma-mcp
分类来源Category source: rules
焦点Focus: design (15)

静态扫描STATIC SCAN

01控制浏览器Controls a browserreadme

**Current Status:** v1.40.9 (Stable) - Production-ready. Latest: Figma's composed colors (a color variable set to another color at an opacit

02读写本地文件Reads and writes local filesreadme

Turn a production codebase into a design system: analyze → extract tokens → scaffold → port components → verify. Local Mode only — these too

扫描发现两个中等风险：控制浏览器和读写本地文件。未发现高风险。

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude/"
    },
    {
      "agent": "claude-desktop",
      "evidence": "readme: …laude Code, Cursor, Windsurf, Claude Desktop, etc.) #### Step 1: Get Your…"
    },
    {
      "agent": "claude-ai",
      "evidence": "readme: …ite Relay** - Web AI clients (Claude.ai, v0, Replit) can design in Fi…"
    },
    {
      "agent": "cursor",
      "evidence": "readme: …ude.json` | | **Cursor** | `~/.cursor/mcp.json` | `%USERPROFILE%\\.cursor\\mcp…"
    },
    {
      "agent": "windsurf",
      "evidence": "readme: …lient** (Claude Code, Cursor, Windsurf, Claude Desktop, etc.) ####…"
    }
  ],
  "apiKey": "add figma-console -s user -e FIGMA_ACCESS_TOKEN=figd_YOUR_TOKEN_HERE -e ENABLE_MCP_APPS",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 10,
      "ai-tools": 3,
      "dev-tools": 4,
      "indie-web": 0,
      "skill-agent": 5,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "mcp-server"
  },
  "localRuntime": "l dependencies — all analysis runs locally **No MCP Apps support? Same audit, pla",
  "skillMdTotal": 0,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 16,
    "browser": 0,
    "devtool": 4,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "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": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme"
  ],
  "skillMdFetched": 0
}