talktofigma-desktop-mcp

Bridge Figma design data with AI assistants via MCP for reading and editing files.

3|Updated May 16, 2026
One-click install
npx skills add https://github.com/Aradotso/design-skills --skill talktofigma-desktop-mcp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: talktofigma-desktop-mcp
Source: https://github.com/Aradotso/design-skills/tree/main/skills/talktofigma-desktop-mcp
Command: npx skills add https://github.com/Aradotso/design-skills --skill talktofigma-desktop-mcp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of making design assets in Figma actionable for AI coding and automation by providing a reliable MCP bridge to read and modify Figma files.

Core Features & Use Cases

  • Connect and route to Figma files: Join a specific Figma file/view channel so the AI can operate in the right context.
  • Read design structure and selections: Fetch pages, nodes by ID, search nodes, and inspect current selection to understand what to change.
  • Create, update, and style components: Create frames, shapes, text, components, apply properties and styles, and export nodes for downstream implementation work.

Quick Start

Instruct your AI to connect to your Figma file by calling the TalkToFigmaDesktop MCP tool join_channel with the channel formatted as FILE_KEY:PAGE_ID:VIEW_ID.

Frequently Asked Questions about talktofigma-desktop-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract design tokens and layers from Figma using AI?

To extract design tokens and layers from Figma using AI, connect to your file by calling the join_channel tool with your FILE_KEY:PAGE_ID:VIEW_ID, then use get_all_nodes or get_node_by_id to fetch the design structure for your AI assistant.

Can I use AI to update Figma layouts and generate components automatically?

Yes, you can use AI to update Figma layouts and generate components by calling create_* operations and set_properties through the MCP bridge, allowing your AI assistant to apply auto layout, create shapes, text, and components directly.

What is TalkToFigma Desktop MCP and how does it bridge Figma with AI assistants?

TalkToFigma Desktop MCP is a bridge that enables AI assistants to read and modify Figma files via a configured MCP stdio server, translating AI instructions into Figma API operations like node creation, styling, and asset export.

Does Cursor or Claude integration support reading and editing Figma files?

Cursor and Claude integration supports reading and editing Figma files by routing AI requests through the TalkToFigma Desktop MCP server, which executes tool calls such as search_nodes, style operations, and export_node on the connected file.

How do I export Figma design assets for code implementation via MCP?

To export Figma design assets for code implementation via MCP, join the correct channel and use the export_node tool call, which allows your AI assistant to retrieve and download the specified design elements for downstream coding workflows.

What are the limitations of using MCP to control Figma files with AI?

A key limitation is that you must join the correct channel formatted as FILE_KEY:PAGE_ID:VIEW_ID before any operations, and all interactions are bound to the configured MCP stdio server, restricting actions to the supported tool calls like get_node_by_id and set_properties.