{
  "slug": "avclabs",
  "name": "AVCLabs Media MCP",
  "vendor": "AVCLabs",
  "official": true,
  "category": "enhancement",
  "featured": false,
  "tagline": "Cloud video upscaling, image restoration, and SAM3 segmentation without a local GPU.",
  "description": "AVCLabs' first-party MCP wraps its cloud enhancement backend: upscale and denoise video to 1080p/2K, enhance or colorize stills, and run Meta's SAM3 to pull pixel-level masks from an image by text prompt. Video runs as an async job (create_task then poll get_task_status) so long clips survive the client timeout. For an agent, this is the desktop Video Enhancer AI workflow reachable as tools — useful for cleaning up archival plates or lifting generated footage that came out soft.",
  "capabilities": [
    "video-upscaling",
    "denoising",
    "image-enhancement",
    "colorization",
    "restoration",
    "segmentation"
  ],
  "tools_sample": [
    "create_task",
    "get_task_status",
    "enhance_video_sync",
    "enhance_image_sync",
    "colorize_image_sync",
    "denoise_image_sync",
    "sam3_predict",
    "get_sam3_task_status"
  ],
  "install": {
    "claude_code": "claude mcp add avclabs -e API_KEY=YOUR_KEY -- npx -y @avclabs.ai/media-mcp@latest",
    "remote_url": null,
    "stdio_command": "npx -y @avclabs.ai/media-mcp@latest"
  },
  "auth": {
    "type": "api_key",
    "env_var": "API_KEY",
    "key_url": "https://mcp.avc.ai/"
  },
  "pricing": "paid",
  "links": {
    "repo": "https://github.com/avclabs/media-mcp",
    "docs": "https://www.avclabs.com/avclabs-mcp.html",
    "site": "https://mcp.avc.ai"
  },
  "added": "2026-08-12",
  "verified": "2026-08-12",
  "notes": "Official but barely trafficked: the repo has 0 stars and was last pushed 15 Jun 2026, and npm @avclabs.ai/media-mcp is on 0.2.1 from 22 May 2026. MIT, Node 18+, thin client over AVCLabs' HTTP backend. Ceiling is 1080p/2K — below what Topaz or the Topaz models on fal will give you, so this is the cheap-and-cloud option, not the finishing one. enhance_video_sync blocks and truncates around 50s; use create_task plus get_task_status for anything real. SAM3 segmentation is image-only, so it is a masking tool, not video roto. The vendor documents a JSON mcpServers block rather than a CLI one-liner — the command above is the same command/args/env in claude mcp add form. Pricing is behind a Buy Now page at mcp.avc.ai/pricing that did not render for verification, so per-job cost is unconfirmed; the generic env var name API_KEY will also collide if you set it globally."
}