Figma MCP Server

Created By
j4ckp0t85a year ago
experimental gen ai mcp server to generate figma tokens
Overview

What is Figma MCP Server?

Figma MCP Server is an experimental AI-powered server designed to generate Figma tokens and facilitate access to Figma design data for coding tools like Cursor, Windsurf, and Cline.

How to use Figma MCP Server?

To use the Figma MCP Server, run the server using the command: npx figma-developer-mcp --figma-api-key=<your-figma-api-key>. After starting the server, connect it to Cursor and use the tools in Cursor's composer to interact with your Figma designs.

Key features of Figma MCP Server?

  • Detailed CSS Extraction: Extracts exact CSS properties from Figma designs.
  • Design Tokens Generation: Automatically generates design tokens in various formats (CSS, SCSS, TypeScript, JSON).
  • Enhanced Rendering: Provides accurate rendering of designs to code, including support for gradients and multi-layered backgrounds.

Use cases of Figma MCP Server?

  1. Extracting detailed CSS properties for web development.
  2. Generating design tokens for consistent styling across projects.
  3. Facilitating AI-assisted design implementation in coding tools.

FAQ from Figma MCP Server?

  • Can I use Figma MCP Server with any Figma file?

Yes! You can use it with any Figma file as long as you have the appropriate access token.

  • Is there a cost to use Figma MCP Server?

No, it is free to use.

  • What programming languages does it support?

The server is built with TypeScript and can generate tokens for various formats.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
j4ckp0t85
Star
0
Language
TypeScript
License
MIT license

Recommend Servers

View All
Payai X402 Tools

8 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago