What does Figma MCP Server do?
It acts as a bridge between MCP‑compatible AI clients (e.g., Claude Desktop) and the Figma API, exposing tools for file operations, comments, projects, components, styles, and webhooks.
@deepsuthar496
Basic information
Interacts with Figma file content, dev resources, comments, and webhooks.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"figma-mcp-server-deepsuthar496": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@deepsuthar496/figma-mcp-server",
"--client",
"claude"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
A Model Context Protocol (MCP) server that integrates with the Figma API, allowing AI assistants to interact with Figma files, comments, components, projects, webhooks, and published styles. It is designed for developers and designers who want to manage Figma resources programmatically through MCP‑enabled clients.
Install via Smithery (npx -y @smithery/cli install @deepsuthar496/figma-mcp-server --client claude) or manually by cloning the repository, running npm install and npm run build. Configure the server in your MCP settings file by providing a FIGMA_ACCESS_TOKEN environment variable along with the command to run the built server.
It acts as a bridge between MCP‑compatible AI clients (e.g., Claude Desktop) and the Figma API, exposing tools for file operations, comments, projects, components, styles, and webhooks.
You must set a `FIGMA_ACCESS_TOKEN` environment variable in your MCP server configuration. The server uses this token to authenticate all Figma API requests.
The server is built with Node.js (via `npm`). No other external runtime dependencies are mentioned beyond the Node.js toolchain.
All data requests are sent directly to the Figma API using your access token. The server itself does not store any data; it forwards responses between the client and Figma.
The README only documents configuring the server with a command and arguments (typical for stdio). No other transports (e.g., HTTP, SSE) are described.
Generate images, videos, music, and voice-overs directly from your AI agent. The full Artlist AI creative suite as an MCP server — works with Claude, ChatGPT, and VS Code, with more platforms coming soon.

Run complete AI fashion photoshoots from ChatGPT, Claude, or Codex. Turn flat-lay, packshot, and mannequin product images into catalog-ready on-model photos and video with saved art direction, automatic QA, and catalog-s

Make AI videos, images, voiceovers and full AI Video Story episodes from Claude, ChatGPT, Cursor or any MCP client, then post them to TikTok, YouTube and Instagram. Veo, Kling, Seedance and more, on your own aicut accoun
The PostNitro MCP server lets AI assistants and agents — Claude (Desktop, Code, and Cowork), Cursor, ChatGPT, and any other Model Context Protocol client — create carousels, image posts, and videos, manage brand kits, a

Curated marketing libraries and an ideation engine for your AI. Connect Selfstorming to Claude, ChatGPT, Codex, Claude Code or Cursor and your assistant works from your project context plus: - 1,800+ award-winning campa
Comments