claude-talk-to-figma-mcp
Enables AI agents to read, analyze, and modify Figma designs, including creating elements, updating styles, and managing comments via the Figma REST API.
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., "@claude-talk-to-figma-mcpChange all #FF6B6B to #E63946 in the document"
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.

Claude AI Agents Talk to Figma MCP
Enable your AI agents to read, analyze, and modify Figma designs.
Works with your favorite agentic tools:
π©π½βπ» Who it's for
UX/UI Teams
Automate repetitive design tasks and maintain brand consistency without manual effort:
Automated accessibility audits - Detect and fix contrast issues in seconds
Bulk style updates - Change colors, typography, or spacing across the entire document with a single command
Visual hierarchy analysis - Get instant feedback on your design structure
Comment triage - Read every review thread you're involved in and reply in bulk, without leaving the chat
Developers
Generate production-ready code directly from designs:
React/Vue/SwiftUI components - From design to code in one step
Code with design tokens - Keep design and development in sync
Reduce handoff friction - Fewer back-and-forth iterations with the design team
Key advantage: Unlike Figma's official MCP which requires a Dev Mode license, this MCP works with any Figma account (even free ones).
Comments included: Figma's Plugin API cannot see comments at all β they only exist in the REST API. This MCP bridges both, so your agent can read and reply to review threads as well as edit the canvas. See Comment tools.
Related MCP server: figmind
π‘ Real-world use cases
Accessibility:
"Find all text with contrast ratio <4.5:1 and suggest colors that meet WCAG AA"
Rebranding:
"Change #FF6B6B to #E63946 in all primary buttons throughout the document"
Design analysis:
"Analyze the visual hierarchy of this screen and suggest improvements based on design principles"
Developer handoff:
"Generate the React component for 'CardProduct' including PropTypes and styles in CSS modules"
Review triage:
"Show me every unresolved comment I'm involved in across the team, flag the ones waiting on my reply, and draft an answer for each"
β‘οΈ Quick installation
Setup: 5 minutes | First automation: 2 minutes
Requirements
Node.js installed
AI client:
Step 1: Install and start the websocket
Enables the Agent to send commands to Figma.
Clone this fork and build it:
git clone https://github.com/litoondev/claude-talk-to-figma-mcp-main.git
cd claude-talk-to-figma-mcp-main
npm install
npm run build # on Windows: npm run build:win
npm run socketβ οΈ Don't use
npx claude-talk-to-figma-mcp. That installs the upstream package, which does not include the comment tools. This fork must be built from source (or installed via the DXT below).
π‘ Tip: In later sessions just run
npm run socketfrom the project folder β you only build once per update.
Step 2: Install the plugin in Figma
Enables Figma to receive commands from the agent and return responses.
In Figma Desktop go to Menu β Plugins β Development β Import plugin from manifest β inside the folder where you installed the MCP, select src/claude_mcp_plugin/manifest.json
Step 3: Configure your Agentic Tool
Enables the agent to use the MCP's read and modify tools.
Claude Desktop
Build the extension with npm run build:dxt, then double-click the generated .dxt. Claude configures itself automatically and prompts you for your Figma token during install β no config file editing needed.
Cursor
Open Cursor Settings β Tools & Integrations
Click "New MCP Server" to open the
mcp.jsonfileAdd this configuration, pointing at your local build:
{
"mcpServers": {
"ClaudeTalkToFigma": {
"command": "node",
"args": ["/absolute/path/to/claude-talk-to-figma-mcp-main/dist/talk_to_figma_mcp/server.cjs"],
"env": { "FIGMA_ACCESS_TOKEN": "figd_your_token_here" }
}
}
} On Windows, escape the backslashes: "H:\\claude-talk-to-figma-mcp-main\\dist\\talk_to_figma_mcp\\server.cjs"
4. Save the file and restart Cursor
Other Agentic Tools
For other tools (Claude Code, Windsurf, VS Code + GitHub Copilot, Cline, Roo Code), you can follow the instructions in the "Configure your Agentic Tool" chapter of the detailed installation guide.
Step 4: Start working
Open the plugin in Figma
Copy the channel ID (bold code inside the green box)
Type in the chat:
Connect to Figma, channel {your-ID}
β Ready to design with AI!
Subsequent work sessions
To use the MCP again in day-to-day work, you don't need to repeat the entire process:
Start the socket: In the terminal, enter the project folder
your-project/claude-talk-to-figma-mcpand runbun run socket(ornpm run socket).Open the plugin in Figma: You'll find it in your recent plugins list.
Connect the AI: Copy the channel ID and tell your agent:
Connect to Figma, channel {your-ID}.
π€ Multi-Agent & Parallel execution
This MCP server supports safe parallel execution out of the box, allowing multiple AI agents (e.g. Claude Code's sub-agents or team swarms) to work simultaneously on your Figma file without locking up the plugin. A built-in command queue processes requests sequentially on the server side, preventing the Figma API from timing out.
Note: Because multiple agents can modify the document simultaneously, relying on implicit page context is unsafe. As a result, stateful commands like
set_current_pageare blocked. All agents must explicitly provide the intendedparentIdparameter when executing any creation or structural modification command (e.g.,create_frame,create_text).
(Special thanks to @mmabas77 for architecting and contributing this feature!)
π³ Alternative: Using Docker
If you prefer Docker or need to run the WebSocket server in a team environment, see the Docker installation guide in the detailed installation documentation.
π οΈ Capabilities
Design analysis
Get document information, current selection, styles
Scan text, audit components, export assets
Element creation
Shapes, text, frames with full style control
Clone, group, organize elements
Modification
Colors, borders, corners, shadows
Auto-layout, advanced typography
Local components and team library components
Comments β see below
π¬ Comment tools
Read and reply to Figma review threads directly from your agent.
Figma's Plugin API has no access to comments β they aren't part of the document tree and are never exposed to plugins. So these tools take a second route: they call Figma's REST API directly. That has two practical consequences:
They need a personal access token (every other tool does not).
They work without the socket running and without
join_channel.
No file URL required
fileKey is optional on every comment tool. Omit it and the server asks the connected plugin which file is open:
You: check all comments
β reads the comments on whatever file you're looking atPass fileKey explicitly only to target a different file β which also works with no plugin channel connected.
Automatic resolution uses
figma.fileKey, which requires the private plugin API. It's available for locally imported and organisation plugins (this project setsenablePrivatePluginApi: true) andundefinedon public plugin builds. If unavailable you get an explicit message rather than a silent failure.
Setup
Create a token at Figma β Account settings β Security β Personal access tokens, with file content: read (add comments: read/write to post replies)
Expose it to the MCP server as
FIGMA_ACCESS_TOKEN:
{
"mcpServers": {
"ClaudeTalkToFigma": {
"command": "node",
"args": ["/absolute/path/to/claude-talk-to-figma-mcp-main/dist/talk_to_figma_mcp/server.cjs"],
"env": { "FIGMA_ACCESS_TOKEN": "figd_your_token_here" }
}
}
}If you installed the DXT instead, skip this β the extension prompts for the token on install and stores it as a secret.
Restart your client and run
check my Figma accountto verify
Full details, DXT install and tuning options in the installation guide.
What you can ask
β
"Check all comments"
β
"Show me every unresolved comment I'm involved in across the team,
and flag the ones waiting on my reply"
β
"Read my open comments, look up the node each one is pinned to,
and draft a reply explaining the fix"
β
"Reply to all my threads from last week confirming they're addressed
in v2 β dry run first"Threads come back with author, pin location, resolved status, timestamps and the node id each comment is attached to β so you can hand that id straight to get_node_info and reason about what the feedback refers to.
π Documentation
Detailed installation β Manual setup, Cursor, Windsurf and other IDEs
Available commands β Complete tool reference
Troubleshooting β Common errors and how to fix them
Contributing β Architecture, testing, contribution guide
Changelog β Version history
π Credits
Based on cursor-talk-to-figma-mcp by Sonny Lazuardi. Adapted for Claude Desktop and extended with new tools by XΓΊlio ZΓ©.
This fork adds the Figma REST comment tools and automatic file-key resolution, maintained by litoondev. For the original project, see arinspunk/claude-talk-to-figma-mcp.
If you want to know about all project contributions, you can visit the "Contributors" chapter of the contribution guide.
π Project status
β Stable production - Tool ready for daily use in design and development teams
π New in 1.2.0:
Read and reply to Figma comments via the REST API
Automatic file-key resolution β no pasting file URLs
Token prompt built into the DXT package
π Under active development:
Complete support for Figma Variables
Enhanced export to Tailwind CSS/SwiftUI
Need something specific?
Propose new ones on GitHub Issues
For issues with the underlying MCP (not the comment tools), consider upstream instead.
Your feedback and contributions keep the project alive. β€οΈ
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.
Related MCP Servers
- Flicense-qualityDmaintenanceAn MCP (Multi-Agent Conversation Protocol) Server that enables interaction with the Figma REST API, auto-generated using AG2's MCP builder.1
- Alicense-qualityDmaintenanceMCP server that connects AI clients to Figma, enabling real-time reading, creation, and modification of designs using natural language.MIT
- AlicenseBqualityDmaintenanceAn MCP server that integrates AI agents with Figma, enabling reading and programmatic modification of designs.41MIT
- Flicense-qualityDmaintenanceMCP server for the Figma API. Lets AI agents fetch designs, nodes, and rendered images from Figma.2,156
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server exposing the Backtest360 engine API as tools for AI agents.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/litoondev/claude-talk-to-figma-mcp-main'
If you have feedback or need assistance with the MCP directory API, please join our Discord server