What runtime does Figma MCP Server require?
Node.js 16 or higher.
@MCP-Mirror
Basic information
Mirror of
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryGet basic information about a Figma file
Get specific nodes from a Figma file
Get component information from a Figma file
Get style information from a Figma file
Get comments from a Figma file
Search for elements in a Figma file by type, name, etc.
Extract all text elements from a Figma file
A Model Context Protocol (MCP) server that connects to Figma’s API, enabling AI tools and LLMs to access and work with your Figma designs. It is designed for designers and developers who want to integrate design data with AI assistants.
Ensure Node.js 16+ and a Figma Personal Access Token. Clone the repository, install dependencies, create a .env file with FIGMA_API_TOKEN, API_KEY, and TRANSPORT_TYPE (default stdio). Build the server with npm run build and start with npm start. Then configure an MCP client such as Claude for Desktop or Cursor using the provided JSON configuration snippets.
Node.js 16 or higher.
The server supports `stdio` for local connections and `sse` for remote connections. The default transport is `stdio`.
You can generate a Personal Access Token in your Figma account settings under the “Personal Access Tokens” section.
`FIGMA_API_TOKEN` and `API_KEY` are required. `TRANSPORT_TYPE` defaults to `stdio`, and `PORT` (used for SSE transport) defaults to 3000

Design your mobile app UI with AI, then have your coding agent build the real app from it.
Design quality gate for AI-generated UI. Scores any live URL against a published contract of deterministic checks, with an A–F grade, a per-check breakdown and AI-slop pattern findings; validates DTCG token files and Lot

Drive Veltake Studio from any AI agent: create film and ad projects, have the Studio agent build scenes on the canvas, price and start renders, export edited cuts, and make single images, video, speech and music in one c

Generate images, video, audio and short films with 140+ AI models from any MCP client. PixelDojo picks the right model (Flux, Seedream, Seedance, Veo, Kling, WAN, Nano Banana, GPT Image), renders it and returns download

EveryGen AI MCP Server lets AI assistants create videos, images, voiceovers, music and complete multi-shot films. Connect your EveryGen AI account, describe what you want, review the credit quote and approve the creation
Comments