The Figma-Context-MCP server provides AI coding agents like Cursor, Windsurf, and Cline with access to Figma layout information. This integration allows AI tools to fetch and utilize Figma design data, significantly improving the accuracy of one-shot designs compared to traditional methods like pasting screenshots.
Watch a demo of building a UI in Cursor with Figma design data
The server simplifies and translates Figma API responses to provide only the most relevant layout and styling information, enhancing AI accuracy.
npx figma-developer-mcp --figma-api-key=<your-figma-api-key>
{
"mcpServers": {
"Framelink Figma MCP": {
"command": "npx",
"args": ["-y", "figma-developer-mcp", "--figma-api-key=<your-figma-api-key>", "--stdio"]
}
}
}
pnpm install
..env.example
to .env
and fill in your Figma API access token.pnpm run dev
.FIGMA_API_KEY
: Your Figma API access token (required).PORT
: The port to run the server on (default: 3333).--version
: Show version number.--figma-api-key
: Your Figma API access token.--port
: The port to run the server on.--stdio
: Run the server in command mode.--help
: Show help menu.npx figma-developer-mcp --figma-api-key=<your-figma-api-key>
Once connected, drop a link to a Figma file in the composer and ask Cursor to perform tasks.
To inspect responses, run the inspect
command:
pnpm inspect
get_figma_data
Fetches information about a Figma file or a specific node within a file.
download_figma_images
(Work in Progress)Downloads SVG and PNG images used in a Figma file.
MCP server to provide Figma layout information to AI coding agents like Cursor.
typescript | ai | mcp | cursor | figma