Figma
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Last reviewed Mar 2, 2026
Install
claude mcp add figma --transport stdio -- npx -y figma-developer-mcpEnvironment variables required:
FIGMA_API_KEY=your-figma-patAvailable tools
| Tool | Description |
|---|---|
| get_design_context | Extract design details and layout information from a Figma file |
| get_screenshot | Capture a screenshot of a specific Figma frame or component |
| get_metadata | Get metadata about a Figma file including pages and components |
| generate_diagram | Generate a visual diagram from structured data |
What it does
The Figma MCP Server bridges the gap between design and development by connecting your AI coding assistant directly to your Figma files. It can read design layouts, extract component structures, capture screenshots, and pull metadata -- enabling the assistant to generate accurate code that matches your designs.
This server is a game-changer for design-to-code workflows. Instead of manually translating Figma mockups into HTML/CSS or React components, your AI assistant can read the design file directly and generate pixel-accurate implementations with the correct spacing, colors, and typography.
Use cases
- Generate React, Vue, or HTML/CSS components that match your Figma designs precisely
- Extract design tokens like colors, spacing, and typography from Figma files
- Capture screenshots of specific frames to use as reference during development
- Compare your implemented UI against the original Figma design for accuracy
- Pull component structures and hierarchies to inform your component architecture
Getting started
- Create a Figma Personal Access Token at figma.com/developers/api#access-tokens. Go to your Figma account settings and generate a new token.
- Set the
FIGMA_API_KEYenvironment variable to your token value. - To use the server, share a Figma file URL with your assistant. It will extract the file key and node IDs to fetch the relevant design data.
- For best results, ensure your Figma files use Auto Layout, proper naming conventions, and component structures -- this helps the assistant generate cleaner, more maintainable code.
Compatibility
Related MCP servers
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.