figma-mcp 0.1.0

Allow your AI coding agents to access figma files & prototypes directly

Figma MCP Python

Allow your AI coding agents to access Figma files & prototypes directly.

Quick Installation

Option 1: Install with pipx (Recommended)

pipx install figma-mcp

Then run:

figma-mcp --figma-api-key=your_figma_api_token

Option 2: Run without installing

pipx run figma-mcp --figma-api-key=your_figma_api_token

Environment Variables Configuration

You can also set your Figma API token as an environment variable:

export FIGMA_API_TOKEN=your_figma_api_token
figma-mcp

Or create a .env file in your working directory:

FIGMA_API_TOKEN=your_figma_api_token

You can generate an API token in your Figma account settings.

MCP Configuration

Configuration File Example

If you're using Cursor, there are two ways to configure:

1. In settings, add an MCP server using the command:

figma-mcp --figma-api-key=your_figma_key

2. Add a .cursor/mcp.json file in your project:

{
	"mcpServers": {
		"figma-python": {
			"command": "figma-mcp",
			"env": {
				"FIGMA_API_TOKEN": "your_figma_api_key"
			}
		}
	}
}

For other IDEs like Windsurf, use an MCP configuration file (e.g., mcp_config.json):

{
  "mcpServers": {
    "figma-python": {
      "command": "figma-mcp",
      "args": [
        "--figma-api-key=your_figma_key"
      ]
    } 
  }
}

Development Setup

If you want to develop or modify this package:

# Clone the repository
git clone https://github.com/yourusername/figma-mcp-python.git
cd figma-mcp-python

# Install uv and set up the environment
curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
source .venv/bin/activate
uv sync

# Run locally
python -m figma_mcp.main