MCP Cursor

Enhance your development workflow with AI-powered MCP tools and extensions for Cursor IDE.

Product

  • MCP Servers
  • Getting Started
  • Documentation
  • Open Source

Resources

  • MCP Specification
  • Cursor IDE
  • MCP GitHub
  • Contributing

Legal

  • Privacy Policy
  • Terms of Service
  • Cookie Policy
Made withfor the developer community
© 2026 MCP Cursor. All rights reserved.
MCP Logo
MCP Cursor
IntroductionMCPs
IntroductionMCPs
3D MCP Cursor Visualization
  1. Home
  2. Servers
  3. Figma MCP
Figma MCP Logo

Figma MCP

Model Context Protocol Integration

Overview

Integrates with the Figma API to enable design file operations, comment management, and access to design assets for AI-driven analysis and collaboration.

Figma

Integrates with the Figma API to enable design file operations, comment management, and access to design assets for AI-driven analysis and collaboration.

Installation Instructions


README: https://github.com/smithery-ai/mcp-figma

mcp-figma

A Model Context Protocol (MCP) server for Figma API integration, designed to be used with Claude and other MCP-compatible AI assistants.

npm version

Features

This MCP server provides access to Figma API functionality:

  • File operations (get file, get nodes, get images)
  • Comments management
  • Team/project management
  • Components and styles access
  • Persistent API key storage

Installation

NPM Installation

# Install globally
npm install -g mcp-figma

# Or install locally in a project
npm install mcp-figma

# Update to latest version
npm update -g mcp-figma

Usage with Claude

  1. Add mcp-figma to your Claude configuration:
"mcp-figma": {
  "command": "npx",
  "args": [
    "-y",
    "mcp-figma"
  ]
}
  1. When using Claude, the first time you'll need to set your Figma API key:
Please use mcp-figma to set my Figma API key: figd_xxxxxxxxxxxxxxxxxxxxxxx

Your API key will be stored in ~/.mcp-figma/config.json and will be automatically loaded in future sessions.

  1. You can verify your API key is configured:
Please use mcp-figma to check my API key status
  1. Then use any of the available Figma API functions:
Please use mcp-figma to get the file with key abc123

Available Tools

The server provides the following tools:

  • set_api_key: Set your Figma API personal access token (saved to config)
  • check_api_key: Check if an API key is already configured
  • get_file: Get a Figma file by key
  • get_file_nodes: Get specific nodes from a Figma file
  • get_image: Get images for nodes in a Figma file
  • get_image_fills: Get URLs for images used in a Figma file
  • get_comments: Get comments on a Figma file
  • post_comment: Post a comment on a Figma file
  • delete_comment: Delete a comment from a Figma file
  • get_team_projects: Get projects for a team
  • get_project_files: Get files for a project
  • get_team_components: Get components for a team
  • get_file_components: Get components from a file
  • get_component: Get a component by key
  • get_team_component_sets: Get component sets for a team
  • get_team_styles: Get styles for a team
  • get_file_styles: Get styles from a file
  • get_style: Get a style by key

For detailed usage examples, see USAGE.md.

License

MIT

Featured MCPs

Github MCP - Model Context Protocol for Cursor IDE

Github

This server provides integration with Github's issue tracking system through MCP, allowing LLMs to interact with Github issues.

Sequential Thinking MCP - Model Context Protocol for Cursor IDE

Sequential Thinking

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process. Break down complex problems into manageable steps, revise and refine thoughts as understanding deepens, and branch into alternative paths of reasoning.

Puppeteer MCP - Model Context Protocol for Cursor IDE

Puppeteer

A Model Context Protocol server that provides browser automation capabilities using Puppeteer. This server enables LLMs to interact with web pages, take screenshots, execute JavaScript, and perform various browser-based operations in a real browser environment.