Figma MCP Server

Give Cursor, Windsurf, Cline, and other AI-powered coding tools access to your Figma files with this Model Context Protocol server.

When Cursor has access to Figma design data, it's way better at one-shotting designs accurately than alternative approaches like pasting screenshots.

Get started quickly, see Configuration for more details:

npx figma-developer-mcp --figma-api-key=<your-figma-api-key>

Enhanced CSS Extraction

This enhanced version of the MCP server can extract and provide detailed CSS properties from Figma designs, making it more accurate when translating designs to code.

Key Features:

- Detailed CSS Properties: Extracts exact CSS values for all elements
- Complete Styling: Includes colors, dimensions, borders, shadows, typography, and more
- Accurate Rendering: Better translation from Figma to code with proper styles instead of screenshots
- Optional Extraction: Configure whether to include detailed CSS properties in the response

Advanced CSS Features:

- Gradient Support: Accurate extraction of linear, radial, and conic gradients
- Multi-layered Backgrounds: Support for multiple fills with proper stacking order
- Text Styling: Complete typography properties including font family, size, weight, line height, and transformations
- Effects & Filters: Support for box-shadow, blur effects, and backdrop filters
- Transformations: Extracts rotation and scale transforms

Example Usage:

When requesting Figma data, you can specify whether to extract detailed CSS properties:

// With detailed CSS properties
const response = await fetch("http://localhost:3333/messages", {
  method: "POST",
  body: JSON.stringify({
    tool: "get_figma_data",
    params: {
      fileKey: "your-file-key",
      nodeId: "your-node-id",
      extractCssProperties: true // default is true
    }
  })
});
// Without detailed CSS properties (more lightweight)

const response = await fetch("http://localhost:3333/messages", {

  method: "POST",

  body: JSON.stringify({

    tool: "get_figma_data",

    params: {

      fileKey: "your-file-key",

      nodeId: "your-node-id",

      extractCssProperties: false

    }

  })

});

Design Tokens Generation

This enhanced version also includes tools to automatically generate design tokens from your Figma designs, which can be exported in various formats to use in your projects.

Supported Token Types:

- Colors: Extracts colors from fills and named color elements
- Typography: Creates complete typography tokens with font families, sizes, weights, etc.
- Spacing: Identifies spacing patterns from appropriately named elements
- Border Radius: Extracts corner radius values
- Shadows: Captures box shadows and elevations
- Opacity: Extracts opacity values
- Gradients: Saves gradient definitions for reuse

Export Formats:

- CSS: Variables in :root {} for direct use in CSS
- SCSS: Variables and mixins for SCSS workflows
- TypeScript: Type-safe constants with TypeScript types
- JSON: Raw data for custom processing

Example Usage:

// Generate design tokens
const response = await fetch("http://localhost:3333/messages", {
  method: "POST",
  body: JSON.stringify({
    tool: "generate_design_tokens",
    params: {
      fileKey: "your-file-key",
      format: "css", // Options: "css", "scss", "ts", "json"
      outputPath: "./src/styles/design-tokens.css", // Optional
      prefix: "my-app-" // Optional prefix for variable names
    }
  })
});

Demo Video

Watch a demo of building a UI in Cursor with Figma design data

<a href="https://glama.ai/mcp/servers/kcftotr525"></a>

How it works

1. Open Cursor's composer in agent mode.
1. Paste a link to a Figma file, frame, or group.
1. Ask Cursor to do something with the Figma file—e.g. implement a design.
1. Cursor will fetch the relevant metadata from Figma and use it to write your code.

This MCP server is specifically designed for use with Cursor. Before responding with context from the Figma API, it simplifies and translates the response so only the most relevant layout and styling information is provided to the model.

Reducing the amount of context provided to the model helps make the AI more accurate and the responses more relevant.

Installation

Running the server quickly with NPM

You can run the server quickly without installing or building the repo using NPM:

```bash
npx figma-developer-mcp --figma-api-key=<your-figma-api-key>