Figma
Figma MCP Server
Official Figma MCP server that brings design context, variables, components, and Code Connect data into AI coding sessions for design-to-code workflows.
Last reviewed Feb 28, 2026
What it does
The Figma MCP Server connects AI coding agents to your Figma files. Agents can extract design variables, components, and layout data, pull context from Make files, and generate code from selected frames. This keeps design system components consistent with your codebase through Code Connect and supports workflows from prototype to production.
Available tools
| Tool | What it does |
|---|---|
get_design_context |
Extract variables, components, and layout data from Figma files |
generate_code_from_frame |
Generate code from a selected Figma frame |
get_make_resources |
Pull code resources from Make files for LLM context |
get_code_connect |
Retrieve Code Connect mappings for design-to-code consistency |
Tool names may vary by installation method (desktop app vs remote server). Check the Figma MCP catalog for your client's supported tools.
Setup by tool
Cursor
Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-developer-mcp", "--stdio"],
"env": {
"FIGMA_API_KEY": "your_figma_personal_access_token"
}
}
}
}
Claude Code
Add to your Claude configuration file:
{
"mcpServers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-developer-mcp", "--stdio"],
"env": {
"FIGMA_API_KEY": "your_figma_personal_access_token"
}
}
}
}
VS Code / GitHub Copilot
Add the same configuration to your MCP client. Alternatively, use the Figma desktop app local server or the remote MCP server at https://mcp.figma.com if your client supports HTTP transport.
Getting a Figma API key
- Open Figma and go to Settings > Account > Personal access tokens
- Click Generate new token
- Name it (e.g., "AI Coding Agent") and copy the token
- Share the relevant Figma files with the token owner
When to use this
- Design-to-code: Agents generate components that match your Figma design system
- Code Connect: Keep generated code aligned with documented component usage
- Variable sync: Pull design tokens and variables into implementation work
- Make context: Move from prototype to production with Make file resources as context
Security considerations
- Use Personal Access Tokens with minimal scopes; tokens can access all files the owner can access
- Do not commit tokens to version control; use environment variables
- Consider read-only access when agents only need to read design context
- Review generated code before merging; design-to-code output may need manual refinement
Compatibility
Related MCP servers
AWS MCP Server
Open source MCP servers from AWS Labs that give AI coding agents access to AWS documentation, best practices, and contextual guidance for building on AWS.
Docker MCP Server
Docker MCP Gateway orchestrates MCP servers in isolated containers, providing secure discovery and execution of Model Context Protocol servers across AI coding tools.
Firebase MCP Server
Experimental Firebase MCP server that gives AI coding agents access to Firestore, Auth, security rules, Cloud Messaging, and project management through the Firebase CLI.