figma-ui-mcp
Allows AI to draw UI on Figma canvas and read designs back, enabling design-to-code workflows.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@figma-ui-mcpdraw a mobile login screen with email input and a primary button"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
figma-ui-mcp
Bidirectional Figma MCP bridge — let AI assistants (Claude Code, Cursor, Windsurf, Antigravity, VS Code Copilot, or any MCP-compatible IDE) draw UI directly on Figma canvas and read existing designs back as structured data, screenshots, or code-ready tokens. No Figma API key needed — works entirely over localhost.
Requires Figma Desktop — the plugin communicates with the MCP server over
localhostHTTP polling. Figma's web app does not allow localhost network access, so Figma Desktop is required.
Claude ──figma_write──▶ MCP Server ──HTTP (localhost:38451)──▶ Figma Plugin ──▶ Figma Document
Claude ◀─figma_read──── MCP Server ◀──HTTP (localhost:38451)── Figma Plugin ◀── Figma DocumentHow the localhost bridge works
The MCP server starts a small HTTP server bound to localhost:38451. The Figma plugin (running inside Figma Desktop) uses long polling — the server holds requests up to 8s until work arrives, flushing immediately when new ops are queued (near-realtime latency <100ms). All traffic stays on your machine — nothing is sent to any external server.
Multi-instance support (v2.3.0+): Multiple Figma files/tabs can connect simultaneously. Each plugin instance sends a sessionId, and the bridge routes operations to the correct session. Use the optional sessionId param in figma_write/figma_read to target a specific file.
Features
Direction | Tool | What it does |
Write |
| Draw frames, shapes, text, prototypes via JS code |
Read |
| Extract node trees, colors, typography, screenshots |
Info |
| Check plugin connection + active sessions |
Docs |
| Get full API reference + examples |
Rules |
| Generate design system rule sheet — tokens, typography, components |
What's new in v2.5
Feature | Description |
| AI-optimized payload for a node — flex layout, token-resolved colors ( |
| List every component instance in a frame with |
| Find component instances that have no description in Figma (no code mapping yet). Prompts AI to ask user for correct import paths. |
New top-level MCP tool — aggregates color tokens, typography styles, variables (all modes), and component catalog into a single markdown rule sheet. Equivalent to official Figma MCP's | |
| |
Resolved variables |
|
Resolved style refs |
|
Instance overrides detail |
|
INSTANCE nodes now expose set name ( | |
| |
Typography tokens |
|
| Apply a local text style to a TEXT node by name in 1 call — auto-loads font. |
STRING variables for fonts |
|
Effects |
|
Gradient fills |
|
Individual corner radii |
|
8-digit hex + rgba alpha |
|
SVG arc (A) + commas | VECTOR |
Icon libraries | 7 free open-source libraries, iOS-filled first: Ionicons → Fluent → Bootstrap → Phosphor → Tabler Filled → Tabler Outline → Lucide. |
Instance overrides |
|
Batch delete |
|
Prototyping |
|
Scroll behavior |
|
Variants & instance swap |
|
Component property definitions (v2.5.24) |
|
Multi-instance | Multiple Figma tabs connect simultaneously via sessions. |
Full version history: see CHANGELOG.md.
Quick Start
Step 1 — Add the MCP server to your AI client
Choose your platform:
# Project scope (default)
claude mcp add figma-ui-mcp -- npx figma-ui-mcp
# Global scope (all projects)
claude mcp add --scope user figma-ui-mcp -- npx figma-ui-mcpEdit config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-ui-mcp"]
}
}
}Edit .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-ui-mcp"]
}
}
}Edit .vscode/mcp.json (project) or add to settings.json (global):
{
"mcp": {
"servers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-ui-mcp"]
}
}
}
}Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-ui-mcp"]
}
}
}Open "..." dropdown at the top of the agent panel
Click "Manage MCP Servers" → "View raw config"
Add to
mcp_config.json:
{
"mcpServers": {
"figma": {
"command": "npx",
"args": ["-y", "figma-ui-mcp"]
}
}
}git clone https://github.com/TranHoaiHung/figma-ui-mcp
cd figma-ui-mcp
npm install
# Then point your MCP client to: node /path/to/figma-ui-mcp/server/index.js⚠️ IMPORTANT: After adding the MCP server, you MUST restart your IDE / AI client (quit and reopen). The MCP server only loads on startup — simply saving the config file is not enough. This applies to Claude Code, Cursor, VS Code, Windsurf, and Antigravity.
Step 2 — Install the Figma plugin
⬇ Download plugin.zip — no git clone needed
Download and unzip
plugin.zipanywhere on your machineOpen Figma Desktop (required — web app cannot access localhost)
Go to Plugins → Development → Import plugin from manifest...
Select
manifest.jsonfrom the unzipped folderRun Plugins → Development → Figma UI MCP Bridge
The plugin UI shows a green dot when the MCP server is connected.
Updating to a newer version
# Step 1 — get the new version + plugin path
npx figma-ui-mcp@latest --version
# figma-ui-mcp v2.5.12 — plugin: /.../.npm/_npx/.../figma-ui-mcp/plugin
# Step 2 — restart Claude / your IDE so the MCP server reloads
# Step 3 — re-link the Figma plugin (manual, one-time per update)
# Figma Desktop → Plugins → Development → Manage plugins in development
# Remove old "Figma UI MCP Bridge" → "+" → Import plugin from manifest...
# Select manifest.json from the plugin path printed in Step 1
# Step 4 — verify
# Ask your AI: "figma_status"
# pluginVersion in the response should match the npm version aboveThe Figma plugin does not auto-update — re-linking (Step 3) is required whenever the plugin changes.
Step 3 — Connect AI to Figma
Tell your AI assistant to connect:
"Connect to figma-ui-mcp"The AI will call figma_status and confirm:
✅ Connected — File: "My Project", Page: "Page 1", Plugin v2.5.5If you see "Plugin not connected", make sure the Figma plugin is running (Step 2).
Step 4 — Start designing with prompts
Once connected, just describe what you want in natural language:
"Use figma-ui-mcp to draw a login screen for mobile"The AI will automatically:
Call
figma_docsto load the API reference and design rulesCall
figma_read get_page_nodesto understand the current canvasCall
figma_writeto create the design on your Figma canvasCall
figma_read screenshotto verify the result
Prompt examples
Prompt | What happens |
| Creates a 390×844 frame with email/password inputs, Apple/Google buttons |
| Extracts colors, typography, spacing from your selection |
| Returns an inline image the AI can analyze |
| Draws a full dashboard layout with charts and stats |
| Creates a product card with image, price, rating, CTA |
| Creates grouped settings with icons and toggles |
Tips for better results
Be specific about style:
"dark theme","glassmorphism","minimal white"gives the AI clear directionMention platform:
"mobile"(390×844),"tablet"(768×1024),"desktop"(1440×900)Iterate: After the first draw, say
"fix the spacing"or"make the buttons bigger"— the AI reads and modifies existing nodesUse selection: Select a frame in Figma and ask
"improve this design"— the AI reads your selection firstMulti-screen flows:
"Now draw the signup screen next to the login screen"— the AI positions frames side by side
Workflow summary
You: "Connect to figma-ui-mcp"
AI: ✅ Connected to Figma
You: "Draw a mobile onboarding screen with 3 steps"
AI: [calls figma_docs → figma_write → figma_read screenshot]
AI: ✅ Done — here's what I created: [inline screenshot]
You: "The title text is not centered"
AI: [calls figma_read get_selection → figma_write modify → screenshot]
AI: ✅ Fixed — text is now centered
You: "Now draw the next onboarding screen beside it"
AI: [reads page_nodes to find position → draws at x+440]
AI: ✅ Done — 2 screens side by sidefigma_status — check connection (always call first)
figma_docs — load API reference (call before drawing)
figma_write — draw / modify UI on canvas
figma_read — extract design data, screenshots, SVGUsage Examples
Draw a screen
Ask Claude: "Draw a dark dashboard with a sidebar, header, and 4 KPI cards"
Claude calls figma_write with code like:
await figma.createPage({ name: "Dashboard" });
await figma.setPage({ name: "Dashboard" });
const root = await figma.create({
type: "FRAME", name: "Dashboard",
x: 0, y: 0, width: 1440, height: 900,
fill: "#0f172a",
});
const sidebar = await figma.create({
type: "FRAME", name: "Sidebar",
parentId: root.id,
x: 0, y: 0, width: 240, height: 900,
fill: "#1e293b", stroke: "#334155", strokeWeight: 1,
});
await figma.create({
type: "TEXT", name: "App Name",
parentId: sidebar.id,
x: 20, y: 24, content: "My App",
fontSize: 16, fontWeight: "SemiBold", fill: "#f8fafc",
});
// ... continueRead a design
Ask Claude: "Read my selected frame and convert it to Tailwind CSS"
Claude calls figma_read with operation: "get_selection", receives the full node tree,
then generates corresponding code.
Screenshot a frame
figma_read → operation: "screenshot" → nodeId: "123:456"Returns a base64 PNG Claude can analyze and describe.
Architecture
figma-ui-mcp/
├── server/
│ ├── index.js MCP server (stdio transport)
│ ├── bridge-server.js HTTP bridge on localhost:38451 (long-poll, multi-session)
│ ├── code-executor.js VM sandbox — safe JS execution + 7-lib icon fetcher
│ ├── tool-definitions.js MCP tool schemas (figma_status / _write / _read / _docs)
│ └── api-docs.js API reference text (served to AI via figma_docs)
├── src/plugin/ Plugin source (concat-built into plugin/code.js)
│ ├── utils.js, svg-path-helpers.js, paint-and-effects.js, read-helpers.js
│ ├── handlers-write.js, handlers-read.js, handlers-read-detail.js,
│ │ handlers-library.js, handlers-tokens.js, handlers-write-ops.js
│ └── main.js
└── plugin/
├── manifest.json Figma plugin manifest
├── code.js Plugin main (auto-generated — 3600+ LOC)
└── ui.html Plugin UI — long-poll client + status dotSecurity
Layer | Protection |
VM sandbox |
|
Localhost only | Bridge binds |
Operation allowlist | 56 predefined operations accepted (WRITE_OPS + READ_OPS) |
Timeout | 30s VM execution + 60-90s per plugin operation (adaptive by op type) |
Body size limit | 5 MB max per request |
Session isolation | Multi-instance sessions scoped by Figma file ID |
Available Write Operations (figma_write)
Core CRUD
Operation | Description |
| Create FRAME / RECTANGLE / ELLIPSE / LINE / TEXT / SVG / VECTOR / IMAGE |
| Update node properties (fill, size, text, layout, etc.) |
| Remove a single node |
| Batch delete multiple nodes in one call |
| Find nodes by type, name, or ID |
| Move node into parent |
create / modify — advanced props available on any node:
Prop | Example | Notes |
|
| Alpha auto-extracted into paint opacity |
|
| Also |
| Same hex/rgba rules | |
|
| All 4 corners |
Individual corners |
| Rounded top sheet pattern |
|
| Types: |
TEXT center |
| Auto-infers |
VECTOR path |
| SVG |
Page Management
Operation | Description |
| Current Figma context info |
| List all pages |
| Switch active page |
| Add a new page |
Node Operations
Operation | Description |
| Duplicate a node with optional repositioning |
| Group multiple nodes |
| Ungroup a GROUP/FRAME |
| Flatten/merge vectors into single path |
| Resize any node |
| Programmatically select nodes |
| Navigate viewport |
| Execute up to 50 ops in one call (10-25x faster) |
Components
Operation | Description |
| List all components in document |
| Convert FRAME/GROUP → reusable Component |
| Create component instance |
| Instantiate with per-layer overrides |
Design Tokens & Styles
Operation | Description |
| Bootstrap complete token system (idempotent) — colors + spacing + typography + text styles + multi-mode in 1 call |
| Create variable collection ("Colors", "Spacing") |
| Create COLOR/FLOAT/STRING/BOOLEAN variable |
| Add mode (e.g. "dark", "compact") |
| Rename a mode |
| Remove a mode |
| Set per-mode value |
| Change variable value — all bound nodes update |
| Bind variable to a node property |
| Apply a local text style to a TEXT node by name (auto-loads font) |
| Pin frame to a variable mode (Light/Dark, Compact/Large) |
| Reset frame to document default mode |
| Create reusable paint style |
| Create reusable text style (manual — prefer |
| Create/get Design Library frame |
| Read library color + text tokens |
applyVariable supported fields — bind FLOAT/COLOR/STRING/BOOLEAN variables to:
Color:
fill,strokeGeometry:
opacity,width,height,strokeWeightCorner radius:
cornerRadius+ individualtopLeftRadius/topRightRadius/bottomLeftRadius/bottomRightRadiusSpacing (auto-layout):
paddingTop,paddingBottom,paddingLeft,paddingRight,itemSpacing,counterAxisSpacingTypography (TEXT nodes):
fontSize,letterSpacing,lineHeight,paragraphSpacing,paragraphIndentFont swap (STRING):
fontFamily,fontStyle,characters— swap Inter → SF Pro via 1 variableVisibility (BOOLEAN):
visible
Image & Icon Helpers (server-side)
Operation | Description |
| Download image → place on canvas |
| Fetch SVG icon with 7-library fallback (iOS-filled first) |
| Icon inside centered circle background |
loadIcon fallback priority (filled-first, iOS style preferred):
Ionicons (iOS filled) → Fluent UI (Win11 filled) → Bootstrap (filled) → Phosphor (filled) → Tabler Filled (4,500+) → Tabler Outline → Lucide (outline fallback)
Free replacement for paid Icons8 ios-filled. Ionicons naming quirks: Bell→notifications, Back→chevron-back, Clock→time, Fire→flame, Lightning→flash, Lock→lock-closed.
Prototyping & Interactions
Operation | Description |
| Add prototype interactions (ON_CLICK/ON_HOVER/ON_PRESS → NAVIGATE/OVERLAY/SWAP) |
| Read all prototype interactions from a node |
| Clear all interactions from a node |
Supported transitions: SMART_ANIMATE, DISSOLVE, MOVE_IN, MOVE_OUT, PUSH, SLIDE_IN, SLIDE_OUT, INSTANT
Supported easings: LINEAR, EASE_IN, EASE_OUT, EASE_IN_AND_OUT, CUSTOM_BEZIER
Scroll Behavior
Operation | Description |
| Set overflow scrolling: |
Variant & Component Swapping
Operation | Description |
| Set variant, boolean, text, or instance swap properties on an INSTANCE |
| Swap the main component of an instance |
| Read all properties + definitions from component/instance |
Available Read Operations (figma_read)
Operation | Description |
| Full design tree of selected node(s) + design tokens |
| Full node tree for a frame/page (depth param: default 10, or "full") |
| Top-level frames on the current page |
| Export node as PNG — displays inline in Claude Code |
| Export node as SVG markup |
| Export node as base64 PNG/JPG — for saving to disk ( |
| AI-optimized design→code payload — flex layout, token-resolved fills as |
| Component instance map — every INSTANCE in a frame with |
| Code-mapping audit — lists instances with no description in Figma ( |
| Structured properties for single node — fills, layout, typography, effects, bound variables (resolved to name+value), style refs (resolved to name+hex), instance overrides (full field list), |
| Ready-to-use CSS string for a node — background, flex, border, radius, shadow, typography, opacity, transform. Best for design-to-code. |
| All local paint, text, effect, grid styles |
| Component listing with descriptions + variant properties |
| Current viewport position, zoom, bounds |
| Local variables (Design Tokens) — collections, modes, values |
| Find nodes by type, name, fill color, font, size — supports |
| Progressive scan for large files — all text, colors, fonts, images, icons |
includeHidden param (boolean, default false) — available on get_selection, get_design, search_nodes, scan_design. When false (default), nodes with visible: false are skipped. Pass true to include hidden layers.
Working with an Existing Project
When opening a Figma file that already has a design system, always read before drawing.
Step 1 — Read what exists
figma_read get_variables → load variable IDs (Design Tokens)
figma_read get_styles → load paint/text style IDs and hex values
figma_read get_local_components → load component IDs
figma_read get_page_nodes → load top-level frame IDsStep 2 — Build lookup maps in figma_write
// Load variables → build varMap: name → id
var vars = await figma.get_variables();
var varMap = {};
for (var ci = 0; ci < vars.collections.length; ci++) {
var col = vars.collections[ci];
for (var vi = 0; vi < col.variables.length; vi++) {
var v = col.variables[vi];
varMap[v.name] = v.id;
}
}
// Load styles → build colorMap: name → hex, textMap: name → {fontSize, fontWeight}
var styles = await figma.get_styles();
var colorMap = {}, textMap = {};
styles.paintStyles.forEach(function(s) { colorMap[s.name] = s.hex; });
styles.textStyles.forEach(function(s) { textMap[s.name] = s; });
// Load components → build compMap: name → id
var comps = await figma.get_local_components();
var compMap = {};
comps.components.forEach(function(c) { compMap[c.name] = c.id; });Step 3 — Create nodes using discovered values
// Use colorMap for fill (hex from existing styles)
var card = await figma.create({
type: "FRAME", name: "Card",
fill: colorMap["color/bg-surface"] || "#FFFFFF",
width: 360, height: 200,
layoutMode: "VERTICAL", paddingTop: 16, paddingLeft: 16,
paddingBottom: 16, paddingRight: 16, itemSpacing: 12,
});
// Then bind variables so light/dark mode switches propagate
if (varMap["bg-surface"])
await figma.applyVariable({ nodeId: card.id, field: "fill", variableId: varMap["bg-surface"] });
if (varMap["radius-md"])
await figma.applyVariable({ nodeId: card.id, field: "cornerRadius",variableId: varMap["radius-md"] });
if (varMap["spacing-md"])
await figma.applyVariable({ nodeId: card.id, field: "paddingTop", variableId: varMap["spacing-md"] });Step 4 — Instantiate components with overrides
// Prefer existing components over drawing from scratch
if (compMap["btn/primary"]) {
await figma.instantiate({
componentId: compMap["btn/primary"],
parentId: card.id,
overrides: { "Label": { text: "Confirm", fill: "#FFFFFF" } }
});
}Step 5 — Pin frames to Light / Dark mode
var collection = vars.collections.find(function(c) { return c.name === "Design Tokens"; });
// Duplicate frame and preview both modes side by side
var frames = await figma.get_page_nodes();
var homeId = frames.find(function(f) { return f.name === "Home"; }).id;
var light = await figma.clone({ id: homeId, x: 0, name: "Preview/Light" });
var dark = await figma.clone({ id: homeId, x: 1540, name: "Preview/Dark" });
await figma.setFrameVariableMode({ nodeId: light.id, collectionId: collection.id, modeName: "light" });
await figma.setFrameVariableMode({ nodeId: dark.id, collectionId: collection.id, modeName: "dark" });Full API reference and all design rules: run
figma_docsin your AI client.
Star History
If figma-ui-mcp helps you, please give it a star — it helps others discover the project!
License
MIT © TranHoaiHung — free to use, modify, and distribute. See LICENSE for details.
Keywords
figma mcp, claude code to figma, cursor to figma, ai to figma, figma ai plugin, figma mcp bridge, figma mcp server, figma design to code, code to figma design, ai ui design, figma automation, figma plugin ai, model context protocol figma, claude figma, windsurf figma, vs code figma, antigravity figma, ai design tool, figma api alternative, figma localhost plugin, draw ui with ai, ai generate figma design, figma design system ai, mcp server figma, figma read design, figma write design, bidirectional figma, figma desktop plugin, npx figma-ui-mcp
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TranHoaiHung/figma-ui-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server