@avclabs.ai/media-mcp

@avclabs.ai/media-mcp · Node.js >=18 · MIT License

Release statusnpm latest is 0.2.1 with 3 video tools and 2 SAM3 tools. The repository's 4 image tools are an unreleased 0.3.0 candidate and are not production-ready yet.

Video enhancement, image enhancement/colorization/denoising, and image segmentation service based on MCP protocol, acting as MCP Client-Server interacting with backend HTTP Server.

Features

The following MCP Tools are provided:

Video Enhancement

create_task - Create a video enhancement task (supports URL or local file upload)
get_task_status - Query task status
enhance_video_sync - Synchronously enhance video (block until completion, default 50s truncation)

Image Enhancement (unreleased 0.3.0 candidate)

enhance_image_sync - Enhance and upscale images (default 50s truncation)
colorize_image_sync - Colorize black-and-white photos (default 50s truncation)
denoise_image_sync - Remove image noise and grain (default 50s truncation)
get_image_task_status - Query image processing task status

Image Segmentation (SAM3)

sam3_predict - SAM3 image segmentation (supports local path, URL, or Base64 image)
get_sam3_task_status - Query SAM3 task status

Usage Examples

After configuration, use natural language to ask your AI:

"Help me enhance this video to 1080p: https://example.com/video.mp4"

"Enhance the video.mp4 on my desktop to 2k quality"

"Help me analyze this image and find all objects in it: C:\Users\xxx\photo.png"

"Use SAM3 to segment this image, prompt is 'find all cars'"

The AI will automatically choose the appropriate sync or async tools based on task complexity to complete the task.

Prerequisites → Lazy Install (Recommended) · Manual Install