mcpField
F
Figma MCP Server

Figma MCP Server

Local
github.com/ishivam06Media & Design0Updated 87w ago

About Figma MCP Server

Figma MCP Server connects MCP-compatible clients to read Figma files and project contents through the Figma API. It also provides tools for managing file variables, references, and themes.

Key features

  1. 01Figma API authentication
  2. 02Retrieve file details
  3. 03List project files
  4. 04Manage variables, references, and themes

Use cases

  1. 01Inspect Figma file details from a client
  2. 02Browse files in a Figma project
  3. 03Create or update file variables
  4. 04Validate references and configure themes

MCP support

An MCP server that exposes Figma file and project access, along with variable, reference, and theme operations, to compatible clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Figma MCP Server

When Claude/Cursor has direct access to Figma design data, it can generate accurate designs in a single step—far more effectively than approaches that rely on screenshots.

A Model Context Protocol (MCP) server providing read-only integration with the Figma API. Supports core Figma file and project access, designed for use with Claude Desktop and other MCP-compatible clients.

Features

  • Secure authentication with Figma API
  • Figma file operations (read, list)

Prerequisites

  • Node.js 18.x or higher
  • Figma access token (read permissions)

Configuration

  1. Copy .env.example to .env and set your Figma access token:
FIGMA_ACCESS_TOKEN=your_figma_token
MCP_SERVER_PORT=3000
DEBUG=figma-mcp:*
  1. For Claude Desktop integration, add the server to your Claude config (see examples/claude_desktop_config.json).
### Available Tools

- **get-file**: Retrieve Figma file details
- **list-files**: List files in a Figma project
- **create-variables**: Create variables in a Figma file
- **update-variables**: Update existing variables in a Figma file
- **delete-variables**: Delete variables from a Figma file
- **create-reference**: Create a reference between variables
- **validate-references**: Check for circular references and validate dependencies
- **create-theme**: Create a theme with variable mode configurations

See `src/handlers/figma.ts` and `src/commands/figma.ts` for implementation details.


See `src/handlers/figma.ts` and `src/commands/figma.ts` for implementation details.

## Project Structure

- `src/server.ts` — Main server logic
- `src/handlers/figma.ts` — Figma API handlers
- `src/commands/figma.ts` — Command definitions
- `src/schemas/` — Input validation schemas
- `src/types/` — TypeScript types
- `bin/figma-mcp-server` — CLI entry point
- `examples/` — Example Claude Desktop configs

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.