Connect

Figma

vkhanhquibyvkhanhqui
•
1.3k
•
Developer Tools
Data Science & ML
Design Tools

Enables unlimited access to Figma file data for AI tools by directly reading files via a plugin, bypassing restrictive API rate limits for free and paid users alike.

Figma-mcp-go offers a free and open-source Figma MCP server designed to eliminate the common problem of API rate limits faced by users integrating Figma with AI tools. Unlike traditional servers that rely on Figma's REST API, which imposes severe call limits, this solution reads Figma file data directly through a plugin bridge. This innovative approach means no Figma API token is required, all operations work locally without cloud calls, and users can experiment extensively with AI tools like Cursor, Claude, and GitHub Copilot without ever encountering rate limits, making it ideal for free plan users and rapid prototyping.

Key Features

01Bypasses all Figma API rate limits, making it free plan friendly.
02Accesses live Figma data directly via a custom plugin bridge, not the REST API.
03Requires no Figma API token and operates entirely locally.
04Provides extensive data retrieval tools for document structure, selection, styles, variables, and components.
05Supports screenshot export of any Figma node directly from the server.
0647 GitHub stars

Use Cases

01Integrating AI-powered design assistants (e.g., Cursor, Claude, Copilot) with Figma without hitting API rate limits.
02Developing and testing AI tools that require real-time Figma document access for analysis or generation.
03Automating design workflows or extracting design system information from Figma files locally and without restrictions.

figma-mcp-go

Figma MCP Server Without API Rate Limits

A free, open-source Figma MCP server that reads Figma files directly via plugin — no REST API, no rate limits. Works with Cursor, Claude, GitHub Copilot, and any MCP-compatible AI tool.

Highlights

  • No Figma API token required
  • No rate limits — free plan friendly
  • Reads live Figma data via plugin bridge
  • Works locally — no cloud calls
  • Written in Go, distributed via npm

Why this exists

Most Figma MCP servers rely on the Figma REST API.

That sounds fine… until you hit this:

Plan Limit
Starter / View / Collab 6 tool calls/month
Pro / Org (Dev seat) 200 tool calls/day
Enterprise 600 tool calls/day

If you're experimenting with AI tools, you'll burn through that in minutes.

I didn't have enough money to pay for higher limits. So I built something that doesn't use the API at all.

Installation & Setup

Install via npx — no build step required. Watch the setup video or follow the steps below.

Watch the video

1. Configure your AI tool

.vscode/mcp.json (Cursor / VS Code / GitHub Copilot)

{
  "servers": {
    "figma-mcp-go": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@vkhanhqui/figma-mcp-go"
      ]
    }
  }
}

.mcp.json (Claude and other MCP-compatible tools)

{
  "mcpServers": {
    "figma-mcp-go": {
      "command": "npx",
      "args": ["-y", "@vkhanhqui/figma-mcp-go"]
    }
  }
}

2. Install the Figma plugin

  1. In Figma Desktop: Plugins → Development → Import plugin from manifest
  2. Select manifest.json from the plugin.zip
  3. Run the plugin inside any Figma file

Available Tools

Document & Selection

Tool Description
get_document Full current page tree
get_metadata File name, pages, current page
get_selection Currently selected nodes
get_node Single node by ID
get_nodes_info Multiple nodes by ID
get_design_context Depth-limited tree — token-efficient for large files
scan_text_nodes All text nodes in a subtree
scan_nodes_by_types Nodes matching given type list

Styles & Variables

Tool Description
get_styles Paint, text, effect, and grid styles
get_variable_defs Variable collections and values
get_local_components All components in the file
get_annotations Dev-mode annotations

Export

Tool Description
get_screenshot Base64 image export of any node
save_screenshots Export images to disk (server-side, no API call)

Related Projects

Contributing

Issues and PRs are welcome.