@tothienbao6a0
MCP server to generate design systems, tokens, and provide Figma layout information to AI coding agents like Cursor
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"Figma MCP Server by Bao To": {
"command": "npx",
"args": [
"-y",
"@tothienbao6a0/figma-mcp-server",
"--figma-api-key=YOUR-KEY",
"--stdio"
]
}
}
}When the nodeId cannot be obtained, obtain the layout information about the entire Figma file
Download SVG and PNG images used in a Figma file based on the IDs of image or icon nodes
Retrieves all variables and variable collections from a Figma file. Variables are different from design tokens - they are Figma's dynamic values system that can store colors, numbers, strings, and booleans with different modes/themes.
Extracts design tokens (colors, typography, spacing, effects) from a Figma file and saves them as a JSON file.
Generates a comprehensive set of Markdown documents detailing the design system from a Figma file into a specified directory.
Compare design tokens between two Figma files or token sets to identify changes, additions, and removals.
Validate design tokens against design system best practices and rules.
Check design tokens for accessibility compliance issues (contrast, text sizes, etc.).
Convert design tokens to different formats (Tailwind, CSS Variables, Style Dictionary, Figma Tokens).
Compare Figma design tokens with code tokens to identify sync issues between design and implementation.
Analyzes Figma components to understand structure, variants, and relationships for intelligent AI-driven code generation. This tool helps AI agents understand component semantics, props, variants, and implementation patterns.
Figma Mcp By Bao To is an advanced Model Context Protocol server that extracts design systems, analyzes components, and maintains design-code consistency from Figma files. Built for AI agents like Cursor and Claude, it transforms static Figma designs into comprehensive, accessible design tokens and documentation.
Install the npm package @tothienbao6a0/figma-mcp-server and configure your AI client to use it. Then paste a Figma file link in your IDE’s chat and ask the AI agent to implement the design, generate tokens, or create documentation. The server fetches and simplifies the relevant Figma metadata automatically.
It is a fork of the original Framelink Figma MCP server, building upon its foundation to offer enhanced capabilities for AI-driven design workflows. It is the only MCP that automatically generates rich, multi‑faceted design system documentation from a Figma link.
No. Only the `get_figma_variables` tool requires a Figma Enterprise plan. Non‑enterprise users can still extract variable‑like structures by calling `generate_design_tokens` with `includeDeducedVariables: true`.
It simplifies and translates responses from the Figma API so that only the most relevant layout and styling information is provided to the AI model. Reducing the amount of context helps make the AI more accurate and responses more relevant.
The server works with Cursor, Claude, and other AI‑powered coding tools that support the Model Context Protocol (MCP).
Tokens can be exported as JSON, CSS Variables, Tailwind, Style Dictionary, and Figma Tokens.
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
Break down any TikTok or Instagram Reels ad and rewrite it for your product, right inside Claude, Cursor, or ChatGPT. Hooks, UGC scripts, and CPM. Free, no API key.
Visual Sandbox runs image, video, audio, 3D and vector models behind one MCP server. Your agent lists the catalogue, reads a model's inputs, estimates the cost, starts a generation and collects the result. You pay per ge
Connect Claude, ChatGPT, and other AI assistants to your social media content, reviews, and UGC aggregated via EmbedSocial.
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
评论