A
licenseNot graded
qualityA
maintenanceEnables MCP-compatible clients to generate images and videos, synthesize speech, clone and design voices, and create related media outputs.
188 npm
MIT
media-gen-mcp
Allows generating images via Meta's AI backend (meta.ai), returning public CDN URLs for the generated images.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@media-gen-mcpgenerate an image of a sunset over the ocean"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
media-gen-mcp
A remote MCP server that lets Claude / ChatGPT generate images (meta.ai) and videos (vibes.ai). Hosted on Render, kept alive 24/7 by UptimeRobot.
Tools
Tool | Backend | Returns |
| meta.ai | inline image + CDN URL(s) |
| meta.ai | edited image inline + URL |
| meta.ai | transparent PNG asset |
| meta.ai | animated GIF |
| meta.ai | full suite: sandbox files, docs, conversions |
| meta.ai | cited web answer |
| meta.ai | structured report |
| meta.ai | IG/FB/Threads summary |
| meta.ai | places w/ address/hours/price |
| vibes.ai | video URL(s) + poster preview |
| vibes.ai i2v | video URL |
| vibes.ai | lip-synced video URL |
| vibes.ai | TTS voice IDs |
| vibes.ai | past media + IDs |
| vibes.ai | ok |
| vibes.ai | ok |
| both | session health |
Media delivery: images are embedded inline in the chat (MCP image content blocks) and returned as public CDN URLs for download. A hourly janitor purges stray temp files so Render's free disk never fills.
Related MCP server: MiniMax MCP JS
Endpoints
GET /health— keep-alive probe (UptimeRobot: HTTP monitor, every 5 min)GET /— info JSONPOST /mcp— MCP Streamable HTTP transport (stateless)
Run locally
pip install -r requirements.txt
python -m uvicorn server:app --host 0.0.0.0 --port 8000Deploy on Render
Push this repo to GitHub.
Render → New → Web Service → connect the repo. It reads
render.yaml, or manually:Build:
pip install -r requirements.txtStart:
uvicorn server:app --host 0.0.0.0 --port $PORTHealth check path:
/health
Optional env var:
META_TOKEN(overrides embedded token).Free plan sleeps after ~15 min idle → UptimeRobot pings
/health.
Connect clients
Claude: Settings → Connectors → Add custom connector →
https://<your-app>.onrender.com/mcpChatGPT: Settings → Apps & Connectors → Create (Developer mode) → MCP Server URL:
https://<your-app>.onrender.com/mcp(no auth)
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Remote MCP for AI video, image, music and speech generation.
Direct AI video, image, music and storyboard production from any MCP client.
Generate images, video, audio and short films with 140+ AI models from any MCP client.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to generate images and videos, synthesize speech, clone and design voices, and dynamically configure API interactions.188 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to generate images and videos, synthesize text-to-speech audio, and clone or design custom voices. It also supports flexible output handling (URLs or local files) and multiple transport modes including stdio, REST, and SSE.188 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to generate images and videos, synthesize speech, clone voices, and design custom voices through integrated AI APIs, with configurable output modes and local or cloud transports.188 npmMIT