{
  "slug": "avclabs",
  "name": "AVCLabs Media MCP",
  "vendor": "AVCLabs",
  "official": true,
  "category": "enhancement",
  "featured": false,
  "tagline": "Cloud video upscaling and SAM3 segmentation without a local GPU, billed by the second.",
  "description": "AVCLabs' first-party MCP wraps its cloud enhancement backend: upscale and denoise video to 1080p/2K, enhance, colorize and denoise 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, as long as the clip is short enough to be worth the credits.",
  "capabilities": [
    "video-upscaling",
    "image-enhancement",
    "colorization",
    "denoising",
    "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": "credits",
  "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": "2026-10-23",
  "caveats": [
    "The entry plan buys about 100 seconds of enhanced footage a month at 1 credit per second, so this is a spot-fix tool, not a pass over a reel.",
    "The ceiling is 1080p/2K, below Topaz, and enhance_video_sync blocks and truncates around 45s, so use create_task plus get_task_status.",
    "SAM3 segmentation is image-only: a masking tool, not video roto.",
    "The generic env var name API_KEY will collide if you set it globally, and uploads are capped at 100MB."
  ],
  "notes": "The image tools finally shipped. npm @avclabs.ai/media-mcp 0.3.0, published 13 Oct 2026 after five months on 0.2.1, carries all nine tools — create_task, get_task_status and enhance_video_sync for video; enhance_image_sync, colorize_image_sync, denoise_image_sync and get_image_task_status for stills; sam3_predict and get_sam3_task_status for masks — so `npx @latest` now does what the README always said it did. On 17 Oct the repo was split into a monorepo of per-function servers (@avclabs.ai/video-mcp, image-mcp, sam3-mcp) so a client only loads the tool schemas it needs, and the all-in-one package was relabelled 'legacy'. Checked 23 Oct 2026: those three split packages are documented in the README but not on npm yet — the registry 404s all of them — so the command above is still the only one that installs. Expect to switch once they publish; the vendor says the legacy package stays configuration-compatible. The repo still sits at 0 stars. Pricing as rendered 10 Sep 2026: 1 credit per second of video and 1 credit per image mask, against Starter $9.95/mo for 100 credits, Pro $25.95 for 300, Advanced $39.95 for 500, or one-time packs from $19.95/50 — so the entry plan buys about 100 seconds of enhanced footage a month, which makes this a spot-fix tool, not a pass over a reel. MIT, Node 18+, 100MB upload cap, thin client over AVCLabs' HTTP backend at mcp.avc.ai; base URLs are overridable via HTTP_API_BASE_URL and SAM3_API_BASE_URL. Ceiling is 1080p/2K — below Topaz or the Topaz models on fal, so this is the cheap-and-cloud option, not the finishing one. enhance_video_sync blocks and truncates around 45s; 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. The generic env var name API_KEY will collide if you set it globally.",
  "evidence": "package_resolves",
  "last_probe": null,
  "package_check": {
    "date": "2026-11-10",
    "registry": "npm",
    "name": "@avclabs.ai/media-mcp",
    "found": true,
    "latest_version": "0.4.0",
    "last_ok": "2026-11-10"
  }
}