Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Marketing media generation — image, video, voice — for AI agents. BYO keys.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
WAVESPEED_API_KEY, FAL_KEY, ELEVENLABS_API_KEY, GEMINI_API_KEY, FIRECRAWL_API_KEY, SCRAPECREATORS_API_KEYValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"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"
}
}
}
}Run this in your terminal
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-skillsFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"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"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"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"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account SupercmoHQ, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: WAVESPEED_API_KEY, FAL_KEY, ELEVENLABS_API_KEY, GEMINI_API_KEY, FIRECRAWL_API_KEY, SCRAPECREATORS_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.27) reached the registry 16 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
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.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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
Only the beginning is shown; read the rest in the repo