Back to MCP directory
publicPublicdnsLocal runtime

figma-mcp

Figma MCP Python是一个允许AI编码代理直接访问Figma文件和原型的工具,支持通过MCP服务器配置快速集成到开发环境中。

article

README

🚀 Figma MCP Python

本项目允许您的 AI 编程代理直接访问 Figma 文件和原型。为开发者在处理 Figma 相关任务时提供便利,提升工作效率。

🚀 快速开始

📦 安装指南

使用 pipx 快速安装

pipx 安装 figma-mcp

不同 IDE 的配置

对于 Cursor

  1. 在设置中添加一个 MCP 服务器,使用以下命令:
figma-mcp --figma-api-key=你的_figma_key
  1. 或者在项目中添加一个 .cursor/mcp.json 文件:
{
  "mcpServers": {
    "figma-python": {
      "command": "figma-mcp",
      "args": [
        "--figma-api-key=你的_figma_key"
      ]
    } 
  }
}

对于其他 IDE(如 Windsurf)

使用 MCP 配置文件(例如 mcp_config.json):

{
  "mcpServers": {
    "figma-python": {
      "command": "figma-mcp",
      "args": [
        "--figma-api-key=你的_figma_key"
      ]
    } 
  }
}

安装 uv 并设置环境

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
source .venv/bin/activate
uv 同步

本地测试

python -m figma_mcp.main

⚠️ 重要提示

有关任何问题或改进建议,请联系:https://x.com/jasonzhou1993

help

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

  1. Open provider connection page
  2. Authorize or copy endpoint
  3. Connect from your MCP client
terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

  1. Copy server_config
  2. Install required package
  3. Fill env variables and restart client