figma

Figma MCP Server Guide

The Figma MCP server brings Figma directly into your workflow by providing important design information and context to AI agents generating code from Figma design files.

Note Rate limits apply to Figma MCP server tools that read data from Figma. Some tools, such as those that write to Figma files, are exempt from the rate limits. Users on the Starter plan or with View or Collab seats on paid plans will be limited to up to 6 tool calls per month. Users with a Dev or Full seat on the Professional, Organization, or Enterprise plans have per minute rate limits, which follow the same limits as the Tier 1 Figma REST API. As with Figma’s REST API, Figma reserves the right to change rate limits.

For the complete set of Figma MCP server docs, see our developer documentation. By using the Figma MCP server and the related resources (including these skills), you agree to the Figma Developer Terms. These skills are currently available as a Beta feature.

Features

• Write to the canvas (remote server only): Create and modify native Figma content directly from your MCP client. With the right skills, agents can build and update frames, components, variables, and auto layout in your Figma files using your design system as the source of truth.

  Note: We're quickly improving how Figma supports AI agents. The write to canvas feature will eventually be a usage-based paid feature, but is currently available for free during the beta period.

• Generate placeholder images: When source, captured, or library images are unavailable, agents can use generate_image after asking permission and disclosing Figma AI credit usage. Generated images are uploaded with upload_assets and applied to the design.

• Generate code from selected frames

  Select a Figma frame and turn it into code. Great for product teams building new flows or iterating on app features.

• Extract design context

  Pull in variables, components, and layout data directly into your IDE. This is especially useful for design systems and component-based workflows.

• Code smarter with Code Connect

  Boost output quality by reusing your actual components. Code Connect keeps your generated code consistent with your codebase.

  Learn more about Code Connect →

• Generate Figma designs from web pages (rolling out)

  Capture, import, or convert a web page into a Figma design directly from your AI coding agent.

Installation & Setup

Connect to the Figma MCP server

Different MCP clients require slightly different setups. Follow the instructions below for your specific client to connect to the Figma MCP server.

VS Code

1. Use the shortcut ⌘ Shift P to search for MCP:Add Server.
2. Select HTTP.
3. Paste the server url https://mcp.figma.com/mcp in the search bar. Then hit Enter.
4. When you're prompted for a server ID, enter figma.
5. Select whether you want to add this server globally or only for the current workspace. Once confirmed, you'll see a configuration like this in your mcp.json file:

{
  "servers": {
    "figma": {
      "type": "http",
      "url": "https://mcp.figma.com/mcp"
    }
  }
}

6. Open the chat toolbar using ⌥⌘B or ⌃⌘I and switch to Agent mode.
7. With the chat open, type in #get_design_context to confirm that the Figma MCP server tools are available. If no tools are listed, restart VS Code.

Note You must have GitHub Copilot enabled on your account to use MCP in VS Code.

For more information, see VS Code's official documentation.

Cursor

The recommended way to set up the Figma MCP server in Cursor is by installing the Figma Plugin, which includes MCP server settings as well as Agent Skills for common workflows.

Install the plugin by typing the following command in Cursor's agent chat:

/add-plugin figma

The plugin includes:

• MCP server configuration for the Figma MCP server
• Skills for implementing designs, connecting components via Code Connect, and creating design system rules
• Rules for proper asset handling from the Figma MCP server

Manual setup

1. Open Cursor → Settings → Cursor Settings.
2. Go to the MCP tab.
3. Click + Add new global MCP server.
4. Enter the following configuration and save:

{
  "mcpServers": {
    "figma": {
      "url": "https://mcp.figma.com/mcp"
    }
  }
}

For more information, see Cursor's official documentation.

Claude Code

The recommended way to set up the Figma MCP server in Claude Code is by installing the Figma Plugin, which includes MCP server settings as well as Agent Skills for common workflows.

Run the following command to install the plugin from Anthropic's official plugin marketplace.

claude plugin install figma@claude-plugins-official

Learn more about Anthropic's Claude Code Plugins and Agent Skills.

Manual setup

1. Open your terminal and run:

claude mcp add --transport http figma https://mcp.figma.com/mcp

2. Use the following commands to check MCP settings and manage servers:

• List all configured servers

  claude mcp list
  

• Get details for a specific server

  claude mcp get my-server
  

• Remove a server

  claude mcp remove my-server
  

For more information, see Anthropic's official documentation.

Gemini CLI

Install the Figma extension for Gemini CLI by running the following command:

gemini extensions install https://github.com/figma/mcp-server-guide

Once installed, authenticate with Figma by running gemini and then executing the following command within the CLI:

/mcp auth figma

To uninstall the extension:

gemini extensions uninstall figma

Other editors

Other code editors and tools that support Streamable HTTP can also connect to the Figma MCP server.

If you're using a different editor or tool, check its documentation to confirm it supports Streamable HTTP based communication. If it does, you can manually add the Figma MCP server using this configuration:

{
  "mcpServers": {
    "figma": {
      "url": "https://mcp.figma.com/mcp"
    }
  }
}

Prompting your MCP client

The Figma MCP server introduces a set of tools that help LLMs translate designs in Figma. Once connected, you can prompt your MCP client to access a specific design node.

To provide Figma design context to your AI client:

1. Copy the link to a frame or layer in Figma.
2. Prompt your client to help you implement the design at the selected URL.

Note Your client won't be able to navigate to the selected URL, but it will extract the node-id that is required for the MCP server to identify which object to return information about.

Tools and skills

Figma maintains a list of tools provided by the Figma MCP server in the developer documentation.

You can also learn more about the skills included with the Figma plugin for supported agents in the Figma Help Center. Depending on the agent, you may also see the terms connector, extension, or power; these include the same set of skills.

This repo also contains standalone workflow skills that are not bundled with the Figma plugin:

• workflow-skills/video-interaction-mapper: Turns UI recordings into annotated Figma storyboards
• workflow-skills/generate-project-plan: Turn a PRD (plus optional codebase grounding) into a FigJam project plan board

MCP best practices

The quality of the generated code depends on several factors. Some controlled by you, and some by the tools you're using. Here are some suggestions for clean, consistent output.

Structure your Figma file for better code

Provide the best context for your design intent, so the MCP and your AI assistant can generate code that's clear, consistent, and aligned with your system.

• Use components for anything reused (buttons, cards, inputs, etc.)
• Link components to your codebase via Code Connect. This is the best way to get consistent component reuse in code. Without it, the model is guessing.
• Use variables for spacing, color, radius, and typography.
• Name layers semantically (e.g. CardContainer, not Group 5)
• Use Auto layout to communicate responsive intent.

Tip Resize the frame in Figma to check that it behaves as expected before generating code.

• Use annotations and dev resources to convey design intent that's hard to capture from visuals alone, like how something should behave, align, or respond.

Write effective prompts to guide the AI

MCP gives your AI assistant structured Figma data, but your prompt drives the result. Good prompts can:

• Align the result with your framework or styling system
• Follow file structure and naming conventions
• Add code to specific paths (e.g. src/components/ui)
• Add or modify code in existing files instead of creating new ones
• Follow specific layout systems (e.g. grid, flexbox, absolute)

Examples:

• "Generate iOS SwiftUI code from this frame"
• "Use Chakra UI for this layout"
• "Use src/components/ui components"
• "Add this to src/components/marketing/PricingCard.tsx"
• "Use our Stack layout component"

Think of prompts like a brief to a teammate. Clear intent leads to better results.

Trigger specific tools when needed

The MCP supports different tools, and each one provides your AI assistant with a different kind of structured context. Sometimes, the assistant doesn't automatically pick the right one, especially as more tools become available. If results are off, try being explicit in your prompt.

• get_design_context provides a structured React + Tailwind representation of your Figma selection. This is a starting point that your AI assistant can translate into any framework or code style, depending on your prompt.
• get_variable_defs extracts the variables and styles used in your selection (color, spacing, typography, etc). This helps the model reference your tokens directly in the generated code.

For example, if you're getting raw code instead of tokens, try something like:

• "Get the variable names and values used in this frame."

Add custom rules

Set project-level guidance to keep output consistent—just like onboarding notes for a new developer. These are things like:

• Preferred layout primitives
• File organization
• Naming patterns
• What not to hardcode

You can provide this in whatever format your MCP client uses for instruction files.

Examples:

Ensure consistently good output