Cursor Talk To Figma MCP Server

What does “Cursor Talk To Figma” MCP Server do?

The Cursor Talk To Figma MCP Server provides a bridge between the Cursor AI development environment and Figma, enabling seamless interaction between AI assistants and design files. By exposing Figma’s design data and actions through the Model Context Protocol (MCP), this server allows developers and AI agents to read, analyze, and modify Figma designs programmatically. This integration streamlines workflows for designers and developers by automating repetitive design tasks, enabling bulk content replacement, propagating component overrides, and offering other automation capabilities directly from AI-powered tools. The server enhances productivity and collaboration by making Figma’s features accessible via standardized MCP endpoints.

List of Prompts

No prompt templates are explicitly listed in the repository or documentation.

List of Resources

No explicit list of MCP resources is provided in the repository or documentation.

List of Tools

No explicit list of MCP tools is included in the repository or server files as presented.

Use Cases of this MCP Server

• Bulk Text Content Replacement: Automate the replacement of text content across multiple Figma designs, reducing manual edits and saving significant time for design teams.
• Instance Override Propagation: Automatically propagate component instance overrides from one source to multiple targets, simplifying repetitive updates in large design systems.
• Design Automation: Enable AI-driven automation of various Figma tasks, such as updating styles, modifying layouts, or generating new design elements, directly from development environments.
• Integrating Figma with AI Agents: Allow AI agents in Cursor to read from and write to Figma files, enabling advanced design analysis, critique, or rapid prototyping.
• Collaborative Development and Design: Bridge the gap between development and design teams by allowing programmatic access to Figma designs from code, fostering tighter integration and faster feedback loops.

How to set it up

Windsurf

1. Ensure you have Bun installed (curl -fsSL https://bun.sh/install | bash).
2. Clone the repository and run bun setup to install dependencies.
3. Start the WebSocket server: bun socket.
4. Add the MCP server to your Windsurf configuration:

   {
     "mcpServers": {
       "cursor-talk-to-figma": {
         "command": "bunx",
         "args": ["cursor-talk-to-figma-mcp"]
       }
     }
   }
   

5. Save configuration and restart Windsurf. Verify the connection to the server.

Securing API Keys:

{
  "mcpServers": {
    "cursor-talk-to-figma": {
      "command": "bunx",
      "args": ["cursor-talk-to-figma-mcp"],
      "env": {
        "FIGMA_API_KEY": "${env.FIGMA_API_KEY}"
      },
      "inputs": {
        "apiKey": "${env.FIGMA_API_KEY}"
      }
    }
  }
}

Claude

1. Install prerequisites (Bun).
2. Run bun setup and bun socket as above.
3. Add the MCP server to your Claude configuration file:

   {
     "mcpServers": {
       "cursor-talk-to-figma": {
         "command": "bunx",
         "args": ["cursor-talk-to-figma-mcp"]
       }
     }
   }
   

4. Save and restart Claude.

Securing API Keys: (see example above)

Cursor

1. Install Bun and run bun setup.
2. Start the WebSocket server: bun socket.
3. Add the following to your Cursor configuration:

   {
     "mcpServers": {
       "cursor-talk-to-figma": {
         "command": "bunx",
         "args": ["cursor-talk-to-figma-mcp"]
       }
     }
   }
   

4. Save and restart Cursor, then verify the MCP server is active.

Securing API Keys: (see example above)

Cline

1. Ensure Bun is installed.
2. Run bun setup and bun socket.
3. In your Cline configuration, add:

   {
     "mcpServers": {
       "cursor-talk-to-figma": {
         "command": "bunx",
         "args": ["cursor-talk-to-figma-mcp"]
       }
     }
   }
   

4. Save, restart Cline, and verify.

Securing API Keys: (see example above)

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "cursor-talk-to-figma": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “cursor-talk-to-figma” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

The repository provides a robust integration for automating Figma via MCP, but lacks detailed documentation of prompts, tools, and resources. The setup instructions and use cases are clear and practical, but deeper MCP-specific features (roots, sampling, etc.) are not documented.

MCP Score

Opinion and Rating:
Based on the two tables, this MCP server earns a 6/10. It is well-starred, actively used, and provides clear setup and valuable integration, but lacks explicit MCP prompt, resource, and tooling documentation, and provides no evidence of roots or sampling support.