What do I need before using the server?
A Figma personal access token (see Figma help on managing tokens) and Node.js installed. You’ll also need a compatible AI tool (Cursor, Windsurf, Cline, or any MCP client).
@1yhy
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"Figma MCP": {
"command": "npx",
"args": [
"figma-mcp",
"--figma-api-key=<your-figma-api-key>",
"--stdio"
]
}
}
}Add a Figma file to your context
Get a thumbnail for a specific node in a Figma file
Get all comments on a Figma file
Post a comment on a node in a Figma file
Reply to an existing comment in a Figma file
Figma MCP is a server based on the Model Context Protocol (MCP) that integrates Figma design files with AI coding tools such as Cursor, Windsurf, and Cline. It converts Figma design data into a format easily understood by AI models, enabling more accurate code generation directly from designs.
Install via npm install -g @yhy2001/figma-mcp-server or from a local .tgz package. Start with figma-mcp --figma-api-key=<your-figma-api-key>. Optionally set a custom --port (default 3333) or use --stdio for command mode. In your AI tool’s MCP configuration, add the server URL (http://localhost:3333/sse) or the npx command with --stdio.
A Figma personal access token (see Figma help on managing tokens) and Node.js installed. You’ll also need a compatible AI tool (Cursor, Windsurf, Cline, or any MCP client).
Follow the official Figma guide: [Manage personal access tokens](https://help.figma.com/hc/en-us/articles/8085703771159-Manage-personal-access-tokens).
No, the server requires internet access to connect to the Figma API and fetch design file data. All design data is retrieved live from Figma.
HTTP/SSE (port 3333 by default) and stdio mode (`--stdio`). Use stdio for tools that launch the server as a subprocess, and SSE for tools that connect to a running server URL.
Yes, it is based on the open-source project Figma-Context-MCP and freely available. You only need your own Figma API token (free tier is sufficient for testing).

Plan, create and schedule social media content from your AI assistant. Blaze makes on-brand posts, carousels and short videos, writes blog posts and newsletters, and schedules them to Instagram, TikTok, YouTube, LinkedIn

Instagram + TikTok content tools inside your AI: download HD posts/reels/carousels, view Instagram stories anonymously, AI-transcribe videos (100+ languages, SRT/VTT/TXT). Requires a Repost PRO subscription.

Run complete AI fashion photoshoots from ChatGPT, Claude, or Codex. Turn flat-lay, packshot, and mannequin product images into catalog-ready on-model photos and video with saved art direction, automatic QA, and catalog-s

Drive Veltake Studio from any AI agent: create film and ad projects, have the Studio agent build scenes on the canvas, price and start renders, export edited cuts, and make single images, video, speech and music in one c

Make AI-drawn video from chat. Claude, Cursor or Claude Code plans the film, the model draws every frame in code at 30 fps, and you edit it on a timeline with narration, music and sound effects.
评论