media-gen-mcp
media-gen-mcp
Un servidor MCP remoto que permite a Claude / ChatGPT generar imágenes (meta.ai) y vídeos (vibes.ai). Alojado en Render, mantenido activo 24/7 por UptimeRobot.
Herramientas
Herramienta | Backend | Devuelve |
| meta.ai | URL(s) pública(s) del CDN de imágenes |
| vibes.ai | URL(s) pública(s) del CDN de vídeos |
| vibes.ai i2v | URL del vídeo en CDN |
| vibes.ai | URL del vídeo con sincronización de labios |
| vibes.ai | IDs de voces TTS |
| vibes.ai | medios anteriores + IDs |
| vibes.ai | ok |
| vibes.ai | ok |
| ambos | estado de la sesión |
El contenido multimedia nunca se almacena en el servidor: los backends devuelven URL públicas del CDN, por lo que no hay nada que limpiar.
Related MCP server: mcp-litmedia
Endpoints
GET /health— sonda mantener activo (UptimeRobot: monitor HTTP, cada 5 min)GET /— JSON de informaciónPOST /mcp— transporte HTTP Streamable de MCP (sin estado)
Ejecutar en local
pip install -r requirements.txt
python -m uvicorn server:app --host 0.0.0.0 --port 8000Desplegar en Render
Sube este repositorio a GitHub.
Render → Nuevo → Servicio web → conecta el repositorio. Usa
render.yaml, o configúralo manualmente:Compilación:
pip install -r requirements.txtInicio:
uvicorn server:app --host 0.0.0.0 --port $PORTRuta de comprobación de estado:
/health
Variable de entorno opcional:
META_TOKEN(sustituye al token integrado).El plan gratuito se suspende después de ~15 min de inactividad → UptimeRobot hace ping a
/health.
Conectar clientes
Claude: Configuración → Conectores → Añadir un conector personalizado →
https://<your-app>.onrender.com/mcpChatGPT: Configuración → Aplicaciones y conectores → Crear (modo de desarrollador) → URL del servidor MCP:
https://<your-app>.onrender.com/mcp(sin autenticación)
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for AI-powered image, audio, and video generation, enabling media creation directly from Claude, Cursor, and other MCP clients.1144MIT
- AlicenseNot gradedqualityDmaintenanceExposes litmedia.ai text-to-image and image-to-video generation tools via MCP, enabling AI agents to generate images and videos directly from prompts.1MIT
- AlicenseAqualityDmaintenanceEnables AI photo generation, editing, and video creation from MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.87MIT
- FlicenseNot gradedqualityDmaintenanceProvides a audio/video creation toolbox via MCP protocol, enabling natural language-based video editing tasks such as image-to-video, video merging, subtitle extraction, and more.3
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
MCP server for QPost — lets AI agents publish video and image posts to YouTube, TikTok, Instagram.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/websitecage-hub/media-gen-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server