Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
作者による説明(英語の原文)
Plan and run local batch image preparation with explicit confirmation before writing files.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
リンク先は作者自身のファイルです。私たちが置いたり再パッケージしたりしたものではありません。ファイルを開くと、Claude Desktopがインストールします。
ターミナルでこれを実行します
claude mcp add image-puma -- npx -y image-pumaプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"image-puma": {
"command": "npx",
"args": [
"-y",
"image-puma"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"image-puma": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"image-puma"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント panth-net で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(1.0.0)がレジストリに届いたのは3 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.js, MCPBも必要です。
同じカテゴリには:Figma Context MCP, Claude Real Video, Figma MCP Server
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Local batch image preparation for the web via a desktop app or directly within your AI via MCP server. Image processing runs locally; Image Puma does not upload your images, require an account, or do any other nonsense. All local image processing.
Download the current Image Puma desktop installer from GitHub Releases:
npm install && npm run make (needs Python 3.11 and access to the gated RMBG-2.0 model for the background remover).The desktop app and MCP server are independent components — install either one on its own, or both together, depending on your needs.
Our installers aren't code-signed. This is a free app, and we'd rather not pay Apple's $99/year developer fee just to make it a "real app" in the eyes of the OS. As a result:
One-click Claude Desktop install uses the .mcpb bundles from GitHub Releases.
Use the following links:
The MCPB installer asks you to choose allowed image folders. Image Puma can only read from and write into those folders.
For coding sessions (optimizing project assets, generating favicons, prepping images for deploys), add the MCP server with one command:
claude mcp add --scope user image-puma -- "$(command -v npx)" -y image-puma mcp serve --transport stdio --allow-dir ~/Pictures ~/Downloads ~/Documents
--scope user makes Image Puma available in every repo and terminal on your machine; leave it off and it only loads in the folder you ran the command from. Swap the folders for whatever Image Puma should be allowed to touch — add a project folder to let it optimize the images in that repo, e.g. "compress every image in assets/ for the web".
Copy that "$(command -v npx)" part exactly — it expands to the full path of npx when you run it. Registering a bare npx looks fine and then fails to connect, because MCP servers are launched with a minimal PATH that doesn't include Node version managers like nvm, fnm, or Volta. See Node not found below.
Then start a new Claude Code session (new conversation in the VS Code extension, or a fresh claude in the terminal) — MCP servers and their commands are discovered at session start, so already-open sessions won't see it. Check it's connected any time with claude mcp list.
If you cloned this repo instead, point the command at your local build (absolute path):
npm install && npm run build:mcp
claude mcp add --scope user image-puma -- "$(command -v node)" /absolute/path/to/Image-Puma/dist/cli.js mcp serve --transport stdio --allow-dir ~/Pictures
Developer install with npx, using an absolute allowed folder path:
{
"mcpServers": { "image-puma": { "command": "/usr/local/bin/npx", "args": [ "-y", "image-puma", "mcp", "serve", "--transport", "stdio", "--allow-dir", "/Users/you/Pictures" ] } } }
Use absolute paths everywhere in mcpServers JSON — for the allowed folders and for command. Run command -v npx in your terminal and paste whatever it prints in place of /usr/local/bin/npx. On native Windows, use "command": "cmd" with "/c" and "npx" as the first two args instead.
Once installed (any of the ways above), just ask Claude in plain language:
You: Compress the images in
~/Pictures/sitefor web upload
Claude: Here's the plan — 14 images accepted, converting to WebP, resized for web, metadata stripped. It lists the exact output paths so you can see nothing gets overwritten. Run it?
You: yes
Claude: Done — 14 of 14 succeeded, 41.8 MB in, 3.6 MB out.
Image Puma always plans first: you see which files it accepted, what settings apply, and where every output will be written — nothing touches disk until you confirm. And it can only see the folders you allowed during install.
Example prompts:
/Users/you/Pictures/site/Users/you/Desktop/photos/Users/you/Downloads/Users/you/Pictures/products/Users/you/Projects/my-app/logo.png into /Users/you/Projects/my-app/public/image-puma commandImage Puma ships one slash command that tells Claude to handle whatever image job you describe with the Image Puma tools — plan first, confirm, then run:
/image-puma compress everything in ~/Pictures/site for the web
In the Claude Code terminal, type /image-puma and the command menu finds it (its full name is /mcp__image-puma__image-puma). In Claude Desktop, the same prompt lives under the + menu in the chat input, listed under Image Puma.
For a bare /image-puma command that also works in the VS Code extension (whose command menu doesn't list MCP prompts), save this as ~/.claude/commands/image-puma.md:
---
description: Batch image work via Image Puma (compress, resize, strip metadata, thumbnails, favicons)
Use the Image Puma MCP tools for this local image task: $ARGUMENTS
If no task was given, ask which images to process and what result is wanted.
Create a plan first with image_puma_plan — plan only, do not run it yet. Pick a preset with image_puma_list_presets, or use custom settings (schema via image_puma_settings_schema). Show the returned plan, warnings, and planned output paths, and call image_puma_run only after the user explicitly confirms.
New sessions then get /image-puma everywhere — terminal and VS Code — as long as the MCP server from "Add it to Claude Code" above is registered.
Quick favicon generation is available through image_puma_generate_favicon.
claude mcp list shows Image Puma as failed, with ENOENT: Executable not found in $PATH: "npx" (or "node"):
image-puma: npx -y image-puma mcp serve ... - ✘ Failed to connect
Your MCP client launches servers with a minimal PATH that never sources ~/.zshrc or ~/.bashrc, so a Node installed through nvm, fnm, Volta, or asdf is invisible to it even though your terminal finds it fine. Fix it by re-registering with an absolute path:
claude mcp remove image-puma -s user
claude mcp add --scope user image-puma -- "$(command -v npx)" -y image-puma mcp serve --transport stdio --allow-dir ~/Pictures
Then start a new session and check claude mcp list again.
One catch if you use nvm: command -v npx resolves to a version-pinned path like ~/.nvm/versions/node/v24.13.1/bin/npx, which stops existing the next time you upgrade Node. Either re-run the two commands above after an upgrade, or point Image Puma at a Node that isn't managed by nvm (/opt/homebrew/bin/node or /usr/local/bin/node) so the path stays valid. Image Puma needs Node 20.3.0 or newer.
Claude Desktop users can skip all of this — the .mcpb bundle above ships with its own Node runtime.
npx image-puma to a local checkoutOn Windows, running npx image-puma ... from inside a directory named image-puma (case-insensitively), such as a clone of this repository, can make npm resolve the package name to that local directory instead of the published package. If the checkout has not been built, the command fails with 'image-puma' is not recognized as an internal or external command.
Run the npx image-puma ... command from a different working directory. When developing from a clone, build it with npm run build:mcp and point the MCP server directly at the local dist/cli.js instead of invoking it through npx.
Run the built-in check, which reports Node version, Sharp, ExifTool, and whether your allowed folders are actually writable:
npx -y image-puma mcp doctor --allow-dir ~/Pictures
Image Puma is released as-is by Pantheon Network. We are not actively fixing bugs or reviewing pull requests. If you'd like to take over maintenance, contact us. Development setup, checks, and the build process are in CONTRIBUTING.md.
Format and OS behavior is documented in docs/support-matrix.md. HEIC/HEIF uses Sharp first. macOS can fall back to ImageIO through sips. Windows and Linux fall back to the bundled libheif decoder when Sharp cannot decode HEVC.