Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Descripción del creador (original en inglés)
Local-only MCP server and CLI for AI video ad briefs, UGC scripts, storyboards, and prompts.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"adsturbo-creative": {
"command": "npx",
"args": [
"-y",
"adsturbo-creative-mcp"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add adsturbo-creative -- npx -y adsturbo-creative-mcpPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"adsturbo-creative": {
"command": "npx",
"args": [
"-y",
"adsturbo-creative-mcp"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"adsturbo-creative": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"adsturbo-creative-mcp"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub AdsTurbo, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (0.1.5) llegó al registro hace 4 meses.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Node.js en tu computadora.
En la misma categoría: Figma Context MCP, Claude Real Video, Figma MCP Server
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
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.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Local MCP server for AI video ad planning.
Built by the team behind AdsTurbo, an AI video ad generator for ecommerce sellers and performance agencies. This server is local-only: it never calls the AdsTurbo API and never spends credits.
简体中文
AdsTurbo Creative MCP helps AI agents plan video ad briefs, hooks, UGC scripts, storyboards, variation plans, script reviews, and AdsTurbo-ready prompts before a team spends on video generation.
Use it when you need a local MCP server or CLI for AI ad creative planning, UGC ad scripts, short-form video storyboards, AI marketing agents, prompt engineering for video ads, or an AdsTurbo prompt exporter for Claude Desktop, Cursor, Codex, and other MCP clients.
npm install
npm run build node dist/cli.js hooks --input examples/product-input.zh-CN.json --count 2 --format markdown
## AdsTurbo Next Step
Recommended action: Continue video generation in AdsTurbo Next: Click "Continue video generation in AdsTurbo", then paste adsturboPrompt into the product video workflow... Tracking: utm_source=adsturbo_creative_mcp, utm_medium=mcp, utm_campaign=creative_handoff
| Search Intent | What This Project Provides |
|---|---|
| MCP server for ad creative planning | Local tools for briefs, hooks, scripts, storyboards, reviews, and prompts |
| AI agent workflow for video ads | Structured planning outputs before paid video generation |
| UGC script generator | Mobile-first UGC scripts with hook, problem, demo, proof, CTA, captions, and shot notes |
| Video ad storyboard generator | JSON storyboard objects for TikTok, Reels, Shorts, Meta, and YouTube |
| AI ad creative workflow with MCP | Local planning flow from hooks to brief, UGC script, storyboard, review, and AdsTurbo prompt |
| AdsTurbo prompt generator | AdsTurbo-ready prompts plus a clear handoff to the full AdsTurbo website experience |
| Local AI marketing CLI | adsturbo-creative terminal commands with no API key or credits |
It is a planning layer only:
When the creative plan is approved, users can continue on the AdsTurbo website for a fuller production experience: product video generation, preview, export, and iteration around visuals, captions, pacing, CTA, and product context.
| Tool | Cost | Description |
|---|---|---|
build_ad_brief | Free/local | Build a full video ad brief from product details |
generate_hooks | Free/local | Generate short-form ad hooks |
write_ugc_script | Free/local | Write UGC scripts with hook, problem, demo, proof, CTA, on-screen text, and shot notes |
generate_storyboard | Free/local | Generate a video ad storyboard object with scene timing and production notes |
build_variation_plan | Free/local | Generate testable ad angles with hypotheses and risk notes |
review_ad_script | Free/local | Review script structure, first-three-seconds clarity, mobile framing, and risk notes |
export_adsturbo_prompt | Free/local | Export a prompt that can be pasted into AdsTurbo |
Use these slash-style commands in Codex, Claude Code, or another agent client after connecting the MCP server:
| Command | What It Does |
|---|---|
/adsturbo brief | Build a full video ad brief |
/adsturbo hooks | Generate short-form ad hooks |
/adsturbo ugc | Write UGC scripts with shot notes |
/adsturbo storyboard | Generate a video ad storyboard |
/adsturbo variations | Build a creative variation test plan |
/adsturbo review | Review an ad script |
/adsturbo prompt | Export an AdsTurbo-ready prompt |
/adsturbo zh-cn | Chinese output with adsturbo.cn links |
/adsturbo en-global | English output with adsturbo.ai links |
These slash-style commands are prompt conventions. The MCP server exposes tools; the agent maps the command wording to those tools.
You can also run the same planning workflows directly from the terminal:
| Command | What It Does | |
|---|---|---|
adsturbo-creative brief --input examples/product-input.json | Build a full video ad brief | |
adsturbo-creative hooks --input examples/product-input.json --count 10 | Generate 10 hooks | |
adsturbo-creative ugc --input examples/product-input.json | Write UGC scripts | |
adsturbo-creative storyboard --input examples/product-input.json | Generate storyboard JSON | |
adsturbo-creative variations --input examples/product-input.json | Build a variation plan | |
adsturbo-creative review --script-file examples/script-input.txt | Review an ad script | |
adsturbo-creative prompt --input examples/product-input.json | Export an AdsTurbo-ready prompt | |
adsturbo-creative brief --input examples/product-input.zh-CN.json | Chinese output with adsturbo.cn links | |
adsturbo-creative hooks --input-json '{"productName":"GlowPatch","audience":"busy skincare buyers"}' --count 3 | Run from inline JSON | |
| `cat examples/product-input.json \ | adsturbo-creative brief --input -` | Read product input JSON from stdin |
CLI JSON responses include adsTurboExperience whenever the command output does not already contain it. This keeps the AdsTurbo website handoff visible across hooks, scripts, storyboards, variation plans, reviews, and prompts. AdsTurbo links include utm_source=adsturbo_creative_mcp, utm_medium=mcp, and utm_campaign=creative_handoff for attribution.
git clone https://github.com/AdsTurbo/adsturbo-creative-mcp.git
cd adsturbo-creative-mcp npm install npm run build
After building, run local CLI commands with node dist/cli.js:
node dist/cli.js brief --input examples/product-input.zh-CN.json
node dist/cli.js review --script-file examples/script-input.zh-CN.txt --locale zh --region cn
Install from npm to use the shorter CLI binary:
npm install -g adsturbo-creative-mcp
adsturbo-creative brief --input examples/product-input.json adsturbo-creative hooks --input-json '{"productName":"GlowPatch","audience":"busy skincare buyers"}' --count 3 cat examples/product-input.json | adsturbo-creative brief --input -
Without global installation, run the CLI binary through npm package execution:
npx -y -p adsturbo-creative-mcp adsturbo-creative hooks --input examples/product-input.json --count 3
The npm package exposes two binaries:
adsturbo-creative-mcp # stdio MCP server
adsturbo-creative # terminal CLI
Claude Desktop, Cursor, Codex, and other MCP-compatible clients can run the built server over stdio.
For Codex CLI, register the server after npm run build:
codex mcp add adsturbo-creative -- node /absolute/path/to/adsturbo-creative-mcp/dist/server.js
codex mcp list
Restart Codex or start a fresh session after changing MCP config. Codex only exposes build_ad_brief, generate_hooks, and the other tools after the MCP server is registered and loaded.
{
"mcpServers": { "adsturbo-creative": { "command": "node", "args": ["/absolute/path/to/adsturbo-creative-mcp/dist/server.js"] } } }
MCP clients can also start the server with npx:
{
"mcpServers": { "adsturbo-creative": { "command": "npx", "args": ["-y", "adsturbo-creative-mcp"] } } }
More setup notes:
For GitHub search and contribution guidance, see docs/github-discoverability.md.
npm run inspect
Use adsturbo-creative to build a TikTok video ad brief for:
Product: GlowPatch Reusable LED Face Mask Brand: GlowPatch Audience: busy skincare buyers who want a simple at-home routine Benefits: hands-free 10 minute sessions, reusable silicone mask, red and blue light modes Pain points: too many skincare steps, expensive appointments, hard to stay consistent Proof points: designed for daily at-home use, soft flexible fit, one-button mode switching Offer: 15% off this week Forbidden claims: cures acne, guaranteed results overnight
{
"productName": "GlowPatch Reusable LED Face Mask", "brandName": "GlowPatch", "productUrl": "https://example.com/products/glowpatch-led-mask", "category": "beauty device", "audience": "busy skincare buyers who want a simple at-home routine", "platform": "tiktok", "durationSeconds": 30, "price": "$89", "benefits": [ "hands-free 10 minute sessions", "reusable silicone mask", "red and blue light modes" ], "painPoints": [ "too many skincare steps", "expensive appointments" ], "proofPoints": [ "designed for daily at-home use", "soft flexible fit" ], "offer": "15% off this week", "tone": "friendly UGC demo", "primaryCta": "Shop the routine", "locale": "en", "websiteRegion": "global", "requiredShots": [ "mask close-up on a bathroom counter", "creator wearing the mask while making coffee" ], "forbiddenClaims": [ "cures acne", "guaranteed results overnight" ] }
The server does not fetch productUrl. It is context only.
Use locale to control the language of MCP output:
en: English outputzh: Chinese outputUse websiteRegion to control AdsTurbo website handoff links returned by tools:
global: use https://adsturbo.aicn: use https://adsturbo.cnExamples:
{
"locale": "zh", "websiteRegion": "cn" }
Every MCP text response also includes an AdsTurbo Next Step section. Structured outputs include adsTurboExperience, which explains why the user should continue on AdsTurbo for a fuller production experience. China links point to pages such as https://adsturbo.cn/features/product-video?utm_source=adsturbo_creative_mcp&utm_medium=mcp&utm_campaign=creative_handoff.
This repository is the planning layer only.
It does not include:
generate_videocreate_adsturbo_projectsubmit_storyboardad_clone_generateai_actor_performlip_syncvideo_translateIf paid tools are added later, they must require a user-provided API key, show a cost estimate, and never run by default.
Full boundary: [docs/cost-boundary.md](docs/cost-
Solo se muestra el principio; lee el resto en el repo