Figma MCP server

Figma MCP Python is a specialized server that enables AI coding agents to directly access and interact with Figma files and prototypes. This integration allows your AI tools to retrieve design information, analyze layouts, and extract assets from Figma designs without manual intervention, streamlining the development workflow between design and implementation.

Installation

The quickest way to install the Figma MCP server is using pipx:

pipx install figma-mcp

You'll need a Figma API key to use this server. You can obtain one from your Figma account settings.

Usage with Different IDEs

Setting Up with Cursor

You have two options for configuring the Figma MCP server with Cursor:

Option 1: Add via Settings

In Cursor settings, add an MCP server using the following command:

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

Replace your_figma_key with your actual Figma API key.

Option 2: Project Configuration File

Create a .cursor/mcp.json file in your project directory with the following content:

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

Setting Up with Other IDEs (like Windsurf)

For other IDEs that support MCP, create a configuration file (e.g., mcp_config.json) with the following content:

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

Manual Installation and Testing

If you prefer to set up a local development environment instead of using pipx:

Set Up Environment with UV

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
source .venv/bin/activate
uv sync

Run Locally for Testing

To test the server locally:

python -m figma_mcp.main

This will start the MCP server on your local machine, allowing your AI coding agents to connect to it and access Figma resources.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.