fm3o5

Figma Comments MCP

Community fm3o5
Updated

A lightweight Model Context Protocol (MCP) server that extends the official Figma MCP with powerful comment management capabilities. While the official Figma MCP focuses on design inspection and editing, this project fills the gap by enabling AI assistants to interact with Figma comments.

Figma Comments MCP

A lightweight Model Context Protocol (MCP) server that adds Figma Comments support to AI assistants such as Claude.

The official Figma MCP provides excellent support for reading and editing designs, but it does not expose Figma comments. This project fills that gap by allowing AI assistants to read, query, and reply to comments using the Figma REST API.

Note: This project is designed to work alongside the official Figma MCP, not replace it.

โœจ Features

  • ๐Ÿ“‹ List all comments in a Figma file
  • ๐Ÿ” Query comments by:
    • Node ID
    • Resolved / Unresolved status
    • Keyword
  • ๐Ÿ’ฌ Reply to existing comments
  • โšก Lightweight and easy to extend
  • ๐Ÿค– Built using the official Model Context Protocol (MCP) SDK

Example Workflow

Using the Official Figma MCP + Figma Comments MCP, Claude can:

  1. Read a selected frame.
  2. Retrieve comments attached to that frame.
  3. Understand the requested changes.
  4. Modify the design.
  5. Reply to the comment once the changes have been completed.

This creates an end-to-end AI-powered design review workflow.

Available Tools

list_comments

Returns all comments from the configured Figma file.

get_unresolved_comments

Returns only unresolved comments.

query_comments

Returns comments using optional filters.

Parameters

Name Type Description
nodeId string Filter by Figma Node ID
resolved boolean Filter resolved/unresolved comments
contains string Search comments by keyword

Example:

{
  "nodeId": "114:24499",
  "resolved": false
}

reply_comment

Replies to an existing Figma comment.

Parameters

{
  "commentId": "1825600097",
  "message": "Implemented. Please review."
}

Project Structure

figma-comments-mcp/
โ”‚
โ”œโ”€โ”€ src/
โ”‚   โ”œโ”€โ”€ config/
โ”‚   โ”‚   โ””โ”€โ”€ env.ts
โ”‚   โ”‚
โ”‚   โ”œโ”€โ”€ figma/
โ”‚   โ”‚   โ”œโ”€โ”€ client.ts
โ”‚   โ”‚   โ””โ”€โ”€ comments.ts
โ”‚   โ”‚
โ”‚   โ”œโ”€โ”€ services/
โ”‚   โ”‚   โ””โ”€โ”€ commentService.ts
โ”‚   โ”‚
โ”‚   โ””โ”€โ”€ server.ts
โ”‚
โ”œโ”€โ”€ .env
โ”œโ”€โ”€ package.json
โ””โ”€โ”€ tsconfig.json

Installation

Clone the repository

git clone https://github.com/<your-username>/figma-comments-mcp.git

Install dependencies

npm install

Create a .env file

FIGMA_TOKEN=your_figma_personal_access_token
FIGMA_FILE_KEY=your_figma_file_key

Start the MCP server

npm run dev

Requirements

  • Node.js 20+
  • Figma Personal Access Token
  • Figma File Key

Tech Stack

  • TypeScript
  • Node.js
  • Axios
  • Model Context Protocol SDK
  • Figma REST API

Roadmap

  • List comments
  • Query comments
  • Reply to comments
  • Remote HTTP MCP support
  • Claude.ai Connector support
  • Better formatted responses
  • Unit tests
  • GitHub Actions CI/CD

Contributing

Contributions, issues, and feature requests are welcome.

If you'd like to improve the project, feel free to open an issue or submit a pull request.

License

MIT License

Acknowledgements

  • Anthropic for the Model Context Protocol (MCP)
  • Figma for the REST API
  • The official Figma MCP team for providing the design-side functionality that this project complements.

MCP Server ยท Populars

MCP Server ยท New

    cauldr0nx

    EspoCRM MCP Server

    Opensource MCP Server for EspoCRM

    Community cauldr0nx
    cisco-open

    Network Sketcher

    Network Sketcher is an AI-ready network design tool with Local MCP, Online, and Offline editions for creating network designs and exporting PowerPoint diagrams and Excel-based configuration data.

    Community cisco-open
    IvanMurzak

    โœจ AI Game Developer โ€” Godot MCP

    Godot-MCP โ€” Model Context Protocol (MCP) integration for the Godot Engine. AI tools for the Godot Editor in C#, with cloud connection to ai-game.dev. Apache-2.0.

    Community IvanMurzak
    cyberlife-coder

    velesdb

    The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL โ€” remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

    Community cyberlife-coder
    abskrj

    velane

    Velane is integration infrastructure agents actually control โ€” 800+ OAuth integrations, sandboxed Bun and Python execution, and a full deployment pipeline managed via MCP

    Community abskrj