#76 · Primary category: AI Design & Prototyping
claude-talk-to-figma-mcp
A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity, etc.) to read, analyze, and modify Figma designs
Project last updated:04/18/26
GitHub Stars
652
Forks
129
Contributors
15
License
MIT
Why we included this project
Design teams whose AI assistants need to do more than talk about a Figma file will get real use out of this MCP server. It connects Claude Desktop, Claude Code, Cursor, and similar agentic tools to a live Figma document through a local websocket and a companion plugin, so the agent can read the canvas, check contrast and visual hierarchy, apply bulk style changes, and generate React or SwiftUI components from selected frames. One practical edge over Figma's official MCP is that it works with any Figma account, including free ones, where the official server requires a paid Dev Mode license. The command set spans analysis and structural edits, and a built-in command queue lets several agents work on the same file in parallel without tripping the Figma API. Teams doing rebranding, accessibility fixes, or design-to-code handoff will get the most value here.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
open-design
Open-source Claude Design alternative: local-first desktop app turning coding agents into a design engine for prototypes, landing pages, dashboards, slides, images, and video, with file exports (HTML, PDF, PPTX, MP4).
impeccable
The design language that makes your AI harness better at design.
gradio
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
tldraw
Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.
next-ai-draw-io
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.