Uber details production uSpec usage: automated component specs across 7 implementation stacks, complete accessibility specs in under 2 minutes, all local (no data leaves network). Strongest enterprise validation in the entire category.
Figma Console MCP
activeMost comprehensive Figma MCP by tool count (57+: 22 read + 35+ write, 11 variable/token management). Uber Engineering Blog validates production uSpec usage across 7 stacks. Hockey-stick npm growth (127/wk Nov → 17.4K/wk Mar). Local WebSocket — no rate limits, data never leaves network.
59/100
Trust
1.1K+
Stars
3
Evidence
Product screenshot

Videos
Reviews, tutorials, and comparisons from the community.
The MCP Tool That’s Changing How I Use Figma
How to Connect Figma to Claude AI using MCP Server
Figma Console MCP: Programmatic Control Over Design Systems (Real Demo)
Repo health
17h ago
Last push
17
Open issues
118
Forks
7
Contributors
Editorial verdict
The enterprise write-access leader. Uber's production uSpec validates this at scale — automated component specs across 7 stacks, accessibility in under 2 minutes. Hockey-stick npm trajectory is fastest-growing in the category. Local WebSocket means no rate limits and no data leaving your network.
Source
GitHub: southleft/figma-console-mcp
Public evidence
Southleft comparison: Official MCP is read-only window, Console MCP is full access. 59+ tools vs 14, WebSocket real-time awareness, variable management where Official has zero.
57+ tools (11 variable/token management), cloud relay mode for web AI clients, WCAG design linting. Fastest-growing npm trajectory in category (127/wk Nov → 17,356/wk Mar).
How does this compare?
See side-by-side metrics against other skills in the same category.
Where it wins
Uber uSpec production usage — strongest enterprise validation in the entire category (thousands of engineers, hundreds of components, 7 stacks)
57+ tools (22 read + 35+ write, 11 variable/token management) — broadest surface area
Hockey-stick npm growth: 127/wk (Nov) → 17,356/wk (Mar) — fastest-growing contender by download trajectory
Local WebSocket architecture — no rate limits, no data leaving your network (Uber blog confirmed)
Cloud relay mode: web AI clients can write to Figma without local Node.js
Design linting (WCAG + quality checks) added v1.13.0
Positions itself as complementary to Official — smart adoption strategy
Actively maintained — pushed 2026-03-18
Where to be skeptical
Only one enterprise case study (Uber). Strong signal, but single-source.
Requires Figma Desktop app + local server setup
1,097 stars — much lower raw community adoption than Framelink or Grab
Self-reported tool counts from creator (TJ Pitre, Southleft CEO), though objectively verifiable
Ranking in categories
Know a better alternative?
Submit evidence and we'll run the full pipeline.
Similar skills

Onlook
72Open-source, local-first WYSIWYG visual editor that writes directly to a Next.js + Tailwind codebase. 24,918 stars — highest in UX/UI category. 'Cursor for Designers' positioning. Bypasses Figma entirely for design-in-code workflows.
Framelink / Figma-Context-MCP
70Community standard for feeding Figma design context to AI coding agents. 13.7K stars, 38.6K npm/week, 11+ editor support. Framework-agnostic descriptive JSON output, listed in Figma's own help docs.

Figma MCP Server Guide
62Official Figma MCP. Trust leader with triple partnership (OpenAI Codex, GitHub Copilot, Claude Code), Code Connect integration, bidirectional since Mar 6 2026. 14 tools, 14+ client support, two server modes.
Cursor Talk to Figma
57Enterprise-trust write-access Figma MCP. Built by Grab ($12B+ market cap). Bypasses Figma API rate limits via plugin architecture. 6,505 stars, 699 forks. Listed in Cursor's official marketplace alongside Amplitude, AWS, Linear, Stripe.
Raw GitHub source
GitHub README peek
Constrained peek so you can sanity-check the source material without leaving the site.
Figma Console MCP Server
Your design system as an API. Model Context Protocol server that bridges design and development—giving AI assistants complete access to Figma for extraction, creation, and debugging.
🆕 Import Once, Update Never — Plugin Bootloader Architecture: The Desktop Bridge plugin now dynamically loads its UI from the MCP server on every launch. Import the manifest once from
~/.figma-console-mcp/plugin/manifest.jsonand you're done forever — server updates, new tools, and bug fixes are delivered automatically. Plus: orphaned process cleanup, cross-file library components, and built-in housekeeping. See changelog →
What is this?
Figma Console MCP connects AI assistants (like Claude) to Figma, enabling:
- 🐛 Plugin debugging - Capture console logs, errors, and stack traces
- 📸 Visual debugging - Take screenshots for context
- 🎨 Design system extraction - Pull variables, components, and styles
- ✏️ Design creation - Create UI components, frames, and layouts directly in Figma
- 🔧 Variable management - Create, update, rename, and delete design tokens
- ⚡ Real-time monitoring - Watch logs as plugins execute
- ☁️ Cloud Write Relay - Web AI clients (Claude.ai, v0, Replit) can design in Figma via cloud pairing
- 🔄 Four ways to connect - Remote SSE, Cloud Mode, NPX, or Local Git
⚡ Quick Start
Choose Your Setup
First, decide what you want to do:
| I want to... | Setup Method | Time |
|---|---|---|
| Create and modify designs with AI | NPX Setup (Recommended) | ~10 min |
| Design from the web (Claude.ai, v0, Replit, Lovable) | Cloud Mode | ~5 min |
| Contribute to the project | Local Git Setup | ~15 min |
| Just explore my design data (read-only) | Remote SSE | ~2 min |
⚠️ Important: Capability Differences
| Capability | NPX / Local Git | Cloud Mode | Remote SSE |
|---|---|---|---|
| Read design data | ✅ | ✅ | ✅ |
| Create components & frames | ✅ | ✅ | ❌ |
| Edit existing designs | ✅ | ✅ | ❌ |
| Manage design tokens/variables | ✅ | ✅ | ❌ |
| Real-time monitoring (console, selection) | ✅ | ❌ | ❌ |
| Desktop Bridge plugin | ✅ | ✅ | ❌ |
| Requires Node.js | Yes | No | No |
| Total tools available | 63+ | 43 | 22 |
Bottom line: Remote SSE is read-only with ~38% of the tools. Cloud Mode unlocks write access from web AI clients without Node.js. NPX/Local Git gives the full 63+ tools with real-time monitoring.
🚀 NPX Setup (Recommended)
Best for: Designers who want full AI-assisted design capabilities.
What you get: All 63+ tools including design creation, variable management, and component instantiation.
Prerequisites
- Node.js 18+ — Check with
node --version(Download) - Figma Desktop installed (not just the web app)
- An MCP client (Claude Code, Cursor, Windsurf, Claude Desktop, etc.)
Step 1: Get Your Figma Token
- Go to Manage personal access tokens in Figma Help
- Follow the steps to create a new personal access token
- Enter description:
Figma Console MCP - Copy the token — you won't see it again! (starts with
figd_)
Step 2: Configure Your MCP Client
Claude Code (CLI):
claude mcp add figma-console -s user -e FIGMA_ACCESS_TOKEN=figd_YOUR_TOKEN_HERE -e ENABLE_MCP_APPS=true -- npx -y figma-console-mcp@latest
Cursor / Windsurf / Claude Desktop:
Add to your MCP config file (see Where to find your config file below):
{
"mcpServers": {
"figma-console": {
"command": "npx",
"args": ["-y", "figma-console-mcp@latest"],
"env": {
"FIGMA_ACCESS_TOKEN": "figd_YOUR_TOKEN_HERE",
"ENABLE_MCP_APPS": "true"
}
}
}
}
📂 Where to Find Your Config File
If you're not sure where to put the JSON configuration above, here's where each app stores its MCP config:
| App | macOS | Windows |
|---|---|---|
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json | %APPDATA%\Claude\claude_desktop_config.json |
| Claude Code (CLI) | ~/.claude.json | %USERPROFILE%\.claude.json |
| Cursor | ~/.cursor/mcp.json | %USERPROFILE%\.cursor\mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | %USERPROFILE%\.codeium\windsurf\mcp_config.json |
Tip for designers: The
~symbol means your home folder. On macOS, that's/Users/YourName/. On Windows, it'sC:\Users\YourName\. You can open these files in any text editor — even TextEdit or Notepad.Can't find the file? If it doesn't exist yet, create it. The app will pick it up on its next restart. Make sure the entire file is valid JSON (watch for missing commas or brackets).
Claude Code users: You can skip manual editing entirely. Just run the
claude mcp addcommand above and it handles everything for you.
Step 3: Connect to Figma Desktop
Desktop Bridge Plugin:
- Open Figma Desktop normally (no special flags needed)
- Go to Plugins → Development → Import plugin from manifest...
- Select
~/.figma-console-mcp/plugin/manifest.json(stable path, auto-created by the MCP server) - Run the plugin in your Figma file — the bootloader finds the MCP server and loads the latest UI automatically
One-time setup. The plugin uses a bootloader that dynamically loads fresh code from the MCP server — no need to re-import when the server updates.
Upgrading from v1.14 or earlier? Your existing plugin still works, but to get the bootloader benefits (no more re-importing), do one final re-import from
~/.figma-console-mcp/plugin/manifest.json. The path is created automatically when the MCP server starts. Runnpx figma-console-mcp@latest --print-pathto see it. After this one-time upgrade, you're done forever.
Step 4: Restart Your MCP Client
Restart your MCP client to load the new configuration.
Step 5: Test It!
Check Figma status
→ Should show connection status with active WebSocket transport
Create a simple frame with a blue background