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)
Marketing media generation — image, video, voice — for AI agents. BYO keys.
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。
WAVESPEED_API_KEY, FAL_KEY, ELEVENLABS_API_KEY, GEMINI_API_KEY, FIRECRAWL_API_KEY, SCRAPECREATORS_API_KEY「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
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。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"supercmo": {
"command": "uvx",
"args": [
"supercmo-skills"
],
"env": {
"WAVESPEED_API_KEY": "your-value",
"FAL_KEY": "your-value",
"ELEVENLABS_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"FIRECRAWL_API_KEY": "your-value",
"SCRAPECREATORS_API_KEY": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add supercmo --env WAVESPEED_API_KEY=your-value --env FAL_KEY=your-value --env ELEVENLABS_API_KEY=your-value --env GEMINI_API_KEY=your-value --env FIRECRAWL_API_KEY=your-value --env SCRAPECREATORS_API_KEY=your-value -- uvx supercmo-skills動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"supercmo": {
"command": "uvx",
"args": [
"supercmo-skills"
],
"env": {
"WAVESPEED_API_KEY": "your-value",
"FAL_KEY": "your-value",
"ELEVENLABS_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"FIRECRAWL_API_KEY": "your-value",
"SCRAPECREATORS_API_KEY": "your-value"
}
}
}
}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": {
"supercmo": {
"type": "stdio",
"command": "uvx",
"args": [
"supercmo-skills"
],
"env": {
"WAVESPEED_API_KEY": "your-value",
"FAL_KEY": "your-value",
"ELEVENLABS_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"FIRECRAWL_API_KEY": "your-value",
"SCRAPECREATORS_API_KEY": "your-value"
}
}
}
}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6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 SupercmoHQ 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。
入力が必要なもの:WAVESPEED_API_KEY, FAL_KEY, ELEVENLABS_API_KEY, GEMINI_API_KEY, FIRECRAWL_API_KEY, SCRAPECREATORS_API_KEY
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(0.1.27)がレジストリに届いたのは16 日前です。
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Python (uv)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。
Open-source skills that empower any AI agent (Claude, Cursor, Codex, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.
Just provide a product photo and a brief. The agent extracts the product details, selects the optimal AI image and video models, casts AI actors, and edits the generated content into finished, campaign-ready assets. It can produce videos of any length while maintaining perfect actor and product consistency.
*The open-source alternative to closed AI marketing agents.*
Install in one command — into Claude Code, Cursor and Codex, whichever you have (needs uv):
npx --yes @supercmo/skills@0.1.27 --all
For Cursor, run it in your project with --cursor --project-dir . so the skills land there too.
Then ask your agent to "set me up": bring your own model keys, or sign in and pay per use with SuperCMO's. If the skills are useful to you, a ⭐ helps other people find them.
UGC video
create an ugc video for this tshirt. it should be a get ready with me reel. snappy. very genz. [product-photo]
Cartoon video ad
create a cartoon video ad in stylized 3D style, promoting my tumbler. make it fun and entertaining. [product-photo]
Product ad video
make me an ad video for this energy drink [product-photo]
A full production studio inside Claude. You provide a product photo and a high level (or detailed) brief.
The AI agent then plans the video → writes the script → generates the AI actor → creates storyboards → generates the video clips → stitches them together, and delivers the final video.
The best part? You stay in charge all along.
Paste this to your coding agent (Cursor, Codex, …):
Run `npx --yes @supercmo/skills@0.1.27 --all`. Once it's installed, run the supercmo-setup skill to complete the setup.
Prefer to run it yourself:
npx --yes @supercmo/skills@0.1.27 --all # every detected host
Run the supercmo-setup skill or ask your agent to "set me up".
Prefer a preview before spending? Every generation supports dry_run — the exact request, no API call.
Rather not set anything up? SuperCMO runs these same skills for you, in the browser:
Starting from your product is faster than describing a video from a blank prompt.
Hand SuperCMO a single product photo and it builds a UGC ad around it - a creator on camera reviewing, unboxing, trying on, or demoing your product:
"Make a 30-second unboxing UGC ad for this product." [attach product photo]
What you get back is not a random clip. You get:
Works inside Claude Code, Cursor, Codex, Hermes - any agent that supports the Agent Skills spec.
| You direct, it produces | SuperCMO doesn't decide what your campaign should say — you do. It handles the production work underneath: scripting to your brief, casting, shooting, editing. It checks in at every step, so you can redirect it mid-run instead of accepting whatever comes out the end. |
| No tool hopping | Making one video ad today means jumping between tools: script in one, images in another, voice in a third, video in a fourth, then stitching it in an editor. SuperCMO does it all from a single brief, in one place. |
| The right model, picked for you | Every AI image/video model works differently and needs different prompting. Knowing that Veo wants one kind of prompt and Kling another — and which to reach for in the first place — is most of the work. SuperCMO's skills already know. You write the brief; it handles the rest. |
| Consistency across every shot | One good clip is easy. Ten clips where the product and the face stay identical is the part that breaks. SuperCMO storyboards before it renders and locks a reference into every generation, so continuity holds across the whole cut. |
| Editing included | It doesn't just hand back a raw 10-second clip. It generates the media, splits long clips, trims footage, adds voiceover, and stitches everything into a finished asset. |
| Pay per use, no subscription | Most marketing tools charge monthly whether you use them or not. SuperCMO doesn't — bring your own vendor keys (free), or generate on SuperCMO's keys and pay per use. No lock-in. |
| Runs where you already work | Inside Claude Code, Cursor, OpenAI Codex, Hermes, Openclaw, or any agent that supports the Agent Skills spec. Your keys and files stay on your machine. |
You act as the creative director, and your agent uses SuperCMO skills to orchestrate the entire production pipeline.
Here is an example of how the skills chain together behind the scenes to execute a complex brief like: *"Make a 1-minute video ad for this product [URL] with a voiceover."*
[Brief] "Make a 1-minute video ad for this product [URL] with a voiceover."
│ ├── 1. Analyze ──> Scrapes the URL to understand the product and fetch product images. │ ├── 2. Plan ──> Breaks the 60s brief into four 15-second shots. │ Writes the script and shot list. │ ├── 3. Image ──> Generates master reference images of the product │ using the best image models. │ ├── 4. Video ──> Generates the 4 video clips. Locks the anchor reference │ into every shot so the product doesn't shape-shift. │ ├── 5. Audio ──> Adds a voiceover, budgeting the script to match the │ exact length of the video. │ └── 6. Stitch ──> Stitches the finished clips together to create one continuous 1-minute video file.
SuperCMO installs a full creative agency into your text-based agent. It doesn't just generate media; it orchestrates the specific steps required to make high-converting ads:
These are the discrete skills installed into your agent to run that pipeline:
| Skill | Description |
|---|---|
| generating-ugc-videos | Produces UGC videos of any length - like review, unboxing, try-on, tutorial and more. It casts the actor, writes the script, and storyboards multiple clips to lock in actor and product consistency. It lets you direct every step to get a cohesive, ready-to-run ad in minutes. |
| generating-ad-videos | Produces a polished, cinematic product commercial in your brand's voice — a no-actor product showcase or an actor-led story ad, at any length. It storyboards every clip to hold your real product identical across cuts, writes the voiceover and casts the actor when the ad calls for one, then stitches it into one ready-to-run spot you approve step by step before anything expensive renders. |
| generating-cartoon-videos | Produces a drawn, animated video for your product — cartoon, anime, illustrated or painted, at any length. Your product either stays exactly as photographed or is drawn into the style, and a cast of characters carries the story around it. It settles one art style, writes the story, draws your cast once so every cut is the same cast, then films it clip by clip and lays a voiceover over the top — with your approval before anything expensive renders. |
| cloning-video-ads | Recreates a video ad you admire with your own product. It watches the reference ad, works out the shots, pacing, camera and voiceover that make it work, then rebuilds the same structure around your product — swapping the product, brand and spoken lines for yours while holding the original's craft. You approve the plan before anything expensive renders, and it comes back as one finished clip. |
| generating-image-ads | Produces a scroll-stopping image ads for your product — one image, or a set in every placement ratio your feed needs. It keeps your real product and your brand identity perfectly consistent across every frame, and shapes the offer and claims you give it
冒頭だけを表示しています。続きはリポジトリで読めます