figmad-mcp
Enables AI agents to interact with Figma to create, read, and manage designs using the Figma REST API and a dedicated plugin. It supports advanced features like UI generation from text, webpage reconstruction in Figma, and design token synchronization with codebases.
README
figmad-mcp
Figma Design MCP Server - Create, capture, and manage Figma designs via AI agents.
Features
- Read Operations: Get files, nodes, components, styles, variables, export images
- Write Operations: Create frames, shapes, text; apply auto-layout; update nodes (requires plugin)
- Capture & Reconstruct: Screenshot webpages and recreate them in Figma
- Generate UI: Create UI designs from text prompts
Setup
1. Install Dependencies
npm install
2. Configure Environment
cp .env.example .env
# Edit .env and add your FIGMA_ACCESS_TOKEN
Get your token at: https://www.figma.com/developers/api#access-tokens
3. Build
npm run build
4. Install Plugin (for write operations)
cd plugin
npm install
npm run build
Then in Figma:
- Menu → Plugins → Development → Import plugin from manifest
- Select
plugin/manifest.json
Usage
With Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"figmad": {
"command": "node",
"args": ["/path/to/figmad-mcp/dist/index.js"],
"env": {
"FIGMA_ACCESS_TOKEN": "your-token-here"
}
}
}
}
Available Tools
Read Operations (REST API - always available)
| Tool | Description |
|---|---|
get_file |
Get Figma file structure |
get_node |
Get specific nodes by ID |
get_components |
List components in a file |
get_styles |
Get color/text/effect styles |
get_variables |
Get design tokens/variables |
export_image |
Export node as PNG/SVG/PDF |
Write Operations (Plugin required)
| Tool | Description |
|---|---|
create_frame |
Create a new frame |
create_rectangle |
Create a rectangle shape |
create_text |
Create text node |
update_node |
Modify node properties |
apply_auto_layout |
Apply auto-layout to frame |
set_fills |
Set fill colors |
delete_node |
Delete a node |
get_selection |
Get current selection |
plugin_status |
Check if plugin is connected |
Orchestrated Tools
| Tool | Description |
|---|---|
capture_webpage |
Screenshot and analyze a webpage |
reconstruct_page |
Recreate captured page in Figma |
generate_ui |
Generate UI from text description |
analyze_codebase |
Extract components and design tokens from code |
sync_design_tokens |
Compare/sync tokens between Figma and code |
Example Prompts
Get the structure of my Figma file: [paste figma URL]
Create a landing page with a header, hero section with headline and CTA button, three feature cards, and a footer
Capture https://example.com and recreate it in Figma
Export the frame "Hero Section" as a PNG
Analyze my React codebase at /path/to/project and extract design tokens
Compare design tokens between my Figma file and codebase
Architecture
┌─────────────┐ ┌─────────────────┐ ┌──────────────────┐
│ AI Agent │────▶│ figmad-mcp │────▶│ Figma Plugin │
│ (Claude) │stdio│ (MCP Server) │ ws │ (runs in Figma) │
└─────────────┘ └────────┬────────┘ └──────────────────┘
│
├──▶ Figma REST API (read operations)
└──▶ Playwright (web capture)
Development
npm run dev # Watch mode
npm run typecheck # Type checking
npm run lint # Linting
cd plugin
npm run watch # Watch plugin changes
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.