figmma
Enables interaction with the Figma API through MCP tools for managing files, projects, and comments, plus a real-time observability dashboard.
README
figmma
MCP server for the Figma API with a real-time observability dashboard.
Install
macOS / Linux (checks for Node.js, installs if missing, registers with all agents):
curl -fsSL https://raw.githubusercontent.com/stuffbucket/figmma/main/install.sh | bash
Windows (PowerShell):
irm https://raw.githubusercontent.com/stuffbucket/figmma/main/install.ps1 | iex
Or via npm (requires Node.js >= 18):
npm install -g @stuffbucket/figmma
The postinstall script automatically registers figmma with Claude Code, VS Code / GitHub Copilot, and Codex CLI.
Configure
Claude Code
Project-level (recommended — runs postinstall automatically):
npm install @stuffbucket/figmma
Or add manually to .mcp.json:
{
"mcpServers": {
"figmma": {
"command": "npx",
"args": ["-y", "@stuffbucket/figmma"]
}
}
}
User-level (available in all projects):
claude mcp add --transport stdio figmma --scope user -- npx -y @stuffbucket/figmma
VS Code / GitHub Copilot
Project-level — add to .vscode/mcp.json (created automatically by npm install):
{
"servers": {
"figmma": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@stuffbucket/figmma"]
}
}
}
User-level — add to VS Code settings (settings.json):
{
"mcp": {
"servers": {
"figmma": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@stuffbucket/figmma"]
}
}
}
}
Codex CLI
Add to .codex/mcp.json (created automatically by npm install):
{
"mcpServers": {
"figmma": {
"command": "npx",
"args": ["-y", "@stuffbucket/figmma"]
}
}
}
Setup
On first run with no Figma API token configured, figmma opens a setup wizard in your browser where you enter your Figma Personal Access Token and team URL.
Configuration is stored at:
- macOS / Linux:
~/.config/figmma/config.json - Windows:
%APPDATA%\figmma\config.json
Environment variables FIGMA_API_TOKEN and FIGMA_TEAM_ID override the config file when set in your MCP client's env block.
Tools
| Tool | Description |
|---|---|
get_current_user |
Show the authenticated Figma user (cached) |
parse_figma_url |
Extract file key and node ID from a Figma URL |
list_team_projects |
List all projects in a team |
list_project_files |
List all files in a project |
get_file_info |
Get file metadata (name, version, last modified) |
search_projects |
Search for files by name across all team projects |
get_file_comments |
Retrieve all comments and threads on a file |
Dashboard
figmma includes a real-time observability dashboard at http://localhost:5183 that shows:
- Live MCP tool calls and Figma API requests
- Connection state and auth status
- An interactive REPL to test tools from the browser
The dashboard starts automatically when the MCP server launches. Run it standalone with:
npx @stuffbucket/figmma-dashboard # or: npm run dev (in the source repo)
Development
git clone https://github.com/stuffbucket/figmma.git
cd figmma
npm ci
npm run dev # Dashboard with Vite HMR
npm run lint # ESLint
npm run typecheck # tsc --noEmit
npm run build # tsc + vite build
npm test # E2E smoke test
make pack # Build + npm pack → figmma-1.0.0.tgz
Uninstall
npm uninstall -g @stuffbucket/figmma
This removes the MCP server entries from .mcp.json, .vscode/mcp.json, and .codex/mcp.json.
License
MIT — see LICENSE.
For a visual walkthrough with screenshots, visit the figmma website.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.