Figma Universal MCP Server
Provides tools for interacting with Figma's API, enabling AI agents to manage and manipulate Figma files, components, and design assets.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Figma Universal MCP Serverlist all components in my Figma project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Figma Universal MCP Server
This repository contains an implementation of an Figma Universal MCP (Model Context Protocol) server. It provides a standardized interface for interacting with Figma's tools and services through a unified API.
The server is built using the Universal MCP framework.
This implementation follows the MCP specification, ensuring compatibility with other MCP-compliant services and tools.
Usage
You can start using Figma directly from agentr.dev. Visit agentr.dev/apps and enable Figma.
If you have not used universal mcp before follow the setup instructions at agentr.dev/quickstart
Related MCP server: figma-ui-mcp
Available Tools
The full list of available tools is at ./src/universal_mcp_figma/README.md
Local Development
š Prerequisites
Ensure you have the following before you begin:
Python 3.11+ (recommended)
uv (install globally with
pip install uv)
š ļø Setup Instructions
Follow the steps below to set up your development environment:
Sync Project Dependencies
uv syncThis installs all dependencies from
pyproject.tomlinto a local virtual environment (.venv).Activate the Virtual Environment
For Linux/macOS:
source .venv/bin/activateFor Windows (PowerShell):
.venv\Scripts\ActivateStart the MCP Inspector
mcp dev src/universal_mcp_figma/server.pyThis will start the MCP inspector. Make note of the address and port shown in the console output.
Install the Application
mcp install src/universal_mcp_figma/server.py
š Project Structure
.
āāā src/
ā āāā universal_mcp_figma/
ā āāā __init__.py # Package initializer
ā āāā server.py # Server entry point
ā āāā app.py # Application tools
ā āāā README.md # List of application tools
āāā tests/ # Test suite
āāā .env # Environment variables for local development
āāā pyproject.toml # Project configuration
āāā README.md # This fileš License
This project is licensed under the MIT License.
Generated with MCP CLI ā Happy coding! š
This server cannot be deployed
Maintenance
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Nifty's MCP server ā exposes tasks, projects, messages, and files as tools for AI agents.
- SupabaseOAuthcom.supabase
MCP server for interacting with the Supabase platform
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables interaction with the Figma API through MCP tools for managing files, projects, and comments, plus a real-time observability dashboard.77 npm2ISC
- AlicenseAqualityBmaintenanceEnables MCP clients to read design structure, take screenshots, create nodes, and edit UI directly on Figma canvas via a bridge between MCP and Figma Desktop.10409 npmMIT

Figma MCP Serverofficial
FlicenseNot gradedqualityBmaintenanceProvides Figma design context to AI agents, enabling code generation, design system integration, and canvas manipulation through MCP.1,977-- AlicenseAqualityBmaintenanceEnables coding agents to interact with the currently open Figma file via local MCP tools, including reading the design, extracting nodes as PNG, React, HTML or CSS, editing the canvas when permitted, and sharing saved component sets.3966 npmMIT