
Figma MCP Server
A TypeScript server that implements the Model Context Protocol, enabling AI-powered design creation in Figma using natural language prompts through Cursor Agent.
Tools
add_figma_file
Add a Figma file to your context
view_node
Get a thumbnail for a specific node in a Figma file
read_comments
Get all comments on a Figma file
post_comment
Post a comment on a node in a Figma file
reply_to_comment
Reply to an existing comment in a Figma file
README
Figma MCP (Model Context Protocol)
A complete solution for creating and modifying Figma designs through Cursor Agent using the Model Context Protocol.
Blog: https://xflux.us/2025/04/06/ai-powered-design-automation-building-a-figma-mcp-with-cursor/
Overview
This project enables AI-powered design creation in Figma using natural language prompts through Cursor Agent. It consists of two main components:
- MCP Server: A Bun + TypeScript server that implements the Model Context Protocol and communicates with the Figma plugin via WebSockets.
- Figma Plugin: A plugin that runs in Figma and executes design operations based on instructions from the MCP server.
With this integration, you can use natural language to:
- Create basic design elements (shapes, text, etc.)
- Design complete page layouts with multiple sections
- Modify existing designs
Repository Structure
- figma-mcp-server/: The MCP server implementation
- figma-plugin/: The Figma plugin for executing design operations
Quick Start
1. Set up the MCP Server
cd figma-mcp-server
cp .env.example .env # Edit this file to add your Figma token
bun install
bun run index.ts
2. Set up the Figma Plugin
cd figma-plugin
npm install
npm run build
Then import the plugin into Figma:
- Open Figma
- Go to Plugins > Development > Import plugin from manifest
- Select the
figma-plugin/manifest.json
file
3. Connect to Cursor Agent
In Cursor:
- Go to Settings > Agent > MCP Servers
- Add a new server with URL:
http://localhost:3000/api/mcp/schema
Detailed Documentation
For more detailed instructions, see:
Example Usage
Once everything is set up, you can use Cursor Agent to create designs with prompts like:
Create a landing page with a header, hero section with heading "Our Product" and subheading "The best solution for your needs", 3 features in the features section, and a footer with contact information.
How It Works
- Cursor Agent receives a natural language prompt
- It sends a structured MCP request to the MCP server
- The MCP server processes the request and sends instructions to the Figma plugin via WebSocket
- The Figma plugin executes the design operations in Figma
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.
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.
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.

E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.