Figma MCP Server MCP Server
io.github.planetabhi/figma-mcp-server
Full Figma REST API coverage as MCP tools—automate design workflows in Claude, Cursor, and VS Code.
What this kind of tool is for
- Scaffold, lint, or restyle a component your agent is already editing.
- Run accessibility, link, or screenshot checks against a local build.
- Turn a design constraint into generated markup the agent can iterate on.
How to compare servers like this
- Framework fit:
- Check the tool targets your stack (React, Vue, plain HTML) before installing it.
- Runtime needs:
- Some browser-driving tools need a local browser or display; read the setup notes first.
- Maintenance signal:
- Frontend tooling churns quickly; recent commits are a good filter.
- Output quality:
- Prefer tools whose generated code you would accept into the repo as-is.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Figma MCP Server MCP server?
The Figma MCP Server is a local MCP server that exposes the complete Figma REST API as self-describing tools, enabling AI agents to interact with Figma files, components, variables, and design data. It works with Claude Desktop, Cursor, VS Code, Gemini CLI, and any MCP client, requiring only a Figma personal access token for authentication.
This server bridges Figma and AI by exposing 50+ Figma API endpoints as MCP tools. You can query files and nodes, manage design tokens and variables, read components and styles, access comments, manage webhooks, and retrieve library analytics—all from Claude or your preferred MCP client. It's useful for automating design workflows, extracting design data, and integrating Figma into AI-driven processes.
How to install Figma MCP Server
Copy-paste configuration for popular MCP clients.
FIGMA_API_KEYrequiredsecretFigma personal access token
{
"mcpServers": {
"figma-mcp-server": {
"command": "bunx",
"args": [
"-y",
"figma-mcp-server"
],
"env": {
"FIGMA_API_KEY": "<YOUR_FIGMA_API_KEY>"
}
}
}
}Tools & capabilities
Tools this server exposes to the agent.
Files and nodes— Query files, node trees, render images, access image fills, metadata, and version historyVariables / design tokens— Read, publish, and bulk modify variables and design tokensComponents and styles— Access components, component sets, and styles across file, published, and team scopesComments and reactions— Read and manage comments and reactions on design filesFolders— Query top-level folders, subfolders, files, and folder metadataUsers— Access user informationDev resources— Retrieve developer resources and documentation linksWebhooks— Manage webhooks (v2) for event subscriptionsLibrary analytics— Get component, style, and variable actions and usagesOrganization— Access activity logs, developer logs, and AI usage (Enterprise)Embeds and payments— Manage embeds and payment-related data
Use cases
- Extract design tokens and variables from Figma files to sync with code or design systems
- Automate bulk updates to components, styles, or variables across Figma projects
- Query file metadata, version history, and node structure to audit design changes
- Generate reports on library usage, component adoption, and design token analytics
- Integrate Figma design data into AI workflows for design-aware code generation or documentation
Figma MCP Server MCP server FAQ
It's an MCP server that exposes the full Figma REST API as tools, letting Claude, Cursor, and other MCP clients interact with Figma files, components, variables, and design data programmatically.
The server itself is free and open-source (MIT License). You need a Figma account and personal access token; most features work on any plan, but variables, library analytics, and org logs require higher-tier Figma plans.
Install via npm (`figma-mcp-server`), add it to your client's config file (pointing to `bunx` as the command), set your `FIGMA_API_KEY` environment variable, and restart the client.
A Figma personal access token, generated in Figma Settings > Security > Personal access tokens. Pass it as the `FIGMA_API_KEY` environment variable in your client config.
No—it requires Bun ≥ 1.2 and must be launched with `bunx`, not `npx`. Node.js is not supported.
Most tools work on any plan. Variables, library analytics, and organization logs require Enterprise or Organization plans; activity/developer logs and AI usage require Enterprise with admin access.
README (reference)
Source of truth, from the repository.
Figma MCP Server
A local MCP server with full Figma REST API coverage. Works with Claude Desktop, Cursor, VS Code, the Gemini CLI, and any MCP client. Available on npm and the official MCP Registry.
How it works
Each Figma REST endpoint is exposed as one self-describing MCP tool, auto-discovered at startup from tools/figma/, so adding an endpoint is just adding a file. Required parameters are validated before each call. It runs over stdio.
Prerequisites
Requires Bun ≥ 1.2. It's Bun-native, so launch it with bunx, not npx (Node isn't supported).
Figma API key
Create a personal access token in Figma under Settings > Security > Personal access tokens > Generate new token. Provide it as FIGMA_API_KEY, ideally in your client config's env block (see below).
Configure your client
Every client uses the same server. Point command at bunx, or its absolute path (which bunx) if the client cannot find it on PATH.
{
"mcpServers": {
"figma": {
"command": "bunx",
"args": ["figma-mcp-server"],
"env": {
"FIGMA_API_KEY": "your_figma_api_key_here"
}
}
}
}
Config file locations:
- Claude Desktop: Settings > Developer > Edit Config (
claude_desktop_config.json) - Cursor:
~/.cursor/mcp.json, or.cursor/mcp.jsonper project - Gemini CLI:
~/.gemini/settings.json
Restart the client after editing its config.
VS Code
Use .vscode/mcp.json (workspace) or your user mcp.json, with a servers key. Instead of hardcoding the token, define an input so VS Code prompts for it securely:
{
"inputs": [
{
"type": "promptString",
"id": "figma-api-key",
"description": "Figma API Key",
"password": true
}
],
"servers": {
"figma": {
"command": "bunx",
"args": ["figma-mcp-server"],
"env": {
"FIGMA_API_KEY": "${input:figma-api-key}"
}
}
}
}
- With
${input:figma-api-key}, VS Code prompts you for the key the first time the server starts, then stores it in your OS secret storage. - To re-enter or clear it: Command Palette → MCP: List Servers → pick the server → reset/edit its inputs.
Tool coverage
Full coverage of the Figma REST API (non-deprecated endpoints), 50 tools across:
- Files and nodes (files, node trees, image rendering, image fills, metadata, version history)
- Variables / design tokens (read, published, bulk modify)
- Components, component sets, and styles (file, published, and team scopes)
- Comments and reactions
- Folders (top-level folders, subfolders, files, metadata)
- Users
- Dev resources
- Webhooks (v2)
- Library analytics (component, style, and variable actions and usages)
- Organization: activity logs, developer logs, AI usage (Enterprise)
- Embeds and payments
Check your MCP client's tool list for the full, always-current list of tool names and parameters.
Plan requirements
Most tools work with any plan's personal access token. These need higher tiers:
- Variables (
list_file_variables,get_published_variables,modify_variables): Enterprise organization. - Library analytics (
get_library_*): Organization or Enterprise plan. - Activity logs, developer logs, AI usage: Enterprise organization with an admin or plan access token.
MIT License · By @planetabhi ⋛⋋( ⊙◊⊙)⋌⋚
Related MCP servers

Ply UI
List, search, and inspect 218 Angular + Tailwind components via MCP for AI agents.
Screenshot any URL and see it, or mint a social card — hosted, SSRF-safe, cached. No Chrome to run.

io.github.prembobby39-gif/uimax-mcp
Frontend expert for Claude Code—automated UI reviews, Lighthouse audits, accessibility checks, and code fixes.

unbrowser by Unchained
Chrome-free MCP web runtime for agents with stateful cookies, DOM queries, and bounded script execution.

PlanetScale
Connect to PlanetScale databases, branches, schema, query insights, and execute SQL

Browser engine for AI agents. HTML in, Semantic Object Model out. 16x fewer tokens.
