figma-developer-mcp
MCP server to provide Figma layout information to AI coding agents like Cursor
The Figma MCP Server connects your Figma designs to the AI: it can read a frame's layout, spacing, colors, and fonts, then generate matching front-end code.
It's especially useful for design-to-code work — no manually measuring pixels or copying color values; the AI pulls straight from the design source data.
What it does for you
Lets your AI read your Figma designs — pull layout, colors, spacing, and component data to turn designs straight into code.
Capabilities
- Read layout and styles from Figma files
- Extract design tokens (color / spacing / type)
- Turn design nodes into frontend code
Once installed, try asking your AI
Say this directly in Claude / Cursor or any client with this server connected
- ›“Convert this Figma component into a React + Tailwind component”
- ›“Extract every color used in this design into a palette”
Why use it
Good for: front-end developers and teams doing pixel-accurate design implementation who want to turn Figma frames into code quickly.
Actively maintained and widely adopted; full health data is shown below.
Works with these clients
- Claude Desktopnpx
- Claude Codenpx
- Cursornpx
- VS Codenpx
- Windsurfnpx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Install / Connect
claude mcp add figma-developer-mcp -- npx -y figma-developer-mcpFollow the official README; env and args vary per server.
🛠️ Maintenance weight 30% · 58 pts
📊 Adoption weight 25% · 77 pts
✅ Usability weight 20% · 55 pts
❤️ Health & community weight 25% · 81 pts
Sources: GitHub API · npm registry · updated 2026-08-19
90-day trend
⭐ stars +0%
📦 weekly downloads +0%
Frequently Asked Questions
What Figma permissions does it need?
It needs a Figma access token to read files — configure it with least privilege.
Which framework's code can it generate?
It provides structured design data; whether the output is React/Vue/Tailwind depends on your AI client and prompt.
Similar / alternative servers
io.github.leMaur/livewire-flux-mcp
Flux UI component and layout docs for AI coding agents. Live from fluxui.dev, Pr
io.github.VonderVuflya/yggdrasil
One shared, durable memory for your AI coding agents — local-first, zero-depende
io.github.yaminbkk/nexusmem
Local-first memory for AI coding agents: shell history with exit codes, git diff
io.github.anup-khanal/aidimag
Persistent, verified memory for AI coding agents: recall, capture, guardrails, r
One email a week, 5 minutes to see what happened in the MCP ecosystem
New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.
One email a week · unsubscribe anytime · no data selling