MCP SERVERSubmit a video for enhancement and poll it to completion, or block until it finishes — plus SAM3 image segmentation.
LABSCO SUMMARY
A short clip finishes while you wait and a long one does not, and forcing every caller through the async path adds a poll loop to jobs that never needed it. Providing both lets the caller choose based on what they are actually submitting. The status tool naming its states explicitly is the practical detail — an agent polling a job needs to know what completion looks like rather than inferring it from the absence of an error. The segmentation tool sits apart from the video work; it is the same vendor's capability rather than part of the same pipeline.
A media processing client with two paths for video enhancement — asynchronous with a status poll, or synchronous blocking — and a separate image segmentation tool.
Node.js 18 or newer, and an AVCLabs API key set as API_KEY in the client block. The one key covers both the video and image enhancement service and SAM3 segmentation. The project's README does not say where to get a key.
One command plus a key — npm install -g @avclabs.ai/media-mcp, then supply credentials
USE CASES
Submit the task, then poll its status until it reports completion, rather than blocking for the length of a render.
Use the synchronous call and get the result back directly, skipping the poll loop entirely.
Run SAM3 inference on the image and get the segmentation result back.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
create_taskCreate a video enhancement task (asynchronous).
Two upload methods are supported:
Parameters:
After creating a task, a task_id is returned immediately. Use get_task_status to poll for results until status becomes "completed" or "failed".
enhance_video_syncSynchronously enhance video (blocks until completion).
Two upload methods are supported:
Parameters:
Best for short videos (estimated processing time < 1 minute). If the task is not completed within 50 seconds, the tool returns early with a task_id. Use get_task_status to continue polling.
get_task_statusQuery video enhancement task status. The status field can be: processing, completed, or failed. If status is processing, wait a few seconds and call this tool again to poll.
sam3_predictAnalyze an image using the SAM3 segmentation API to generate inference results (masks, boxes, scores). The image can be provided in one of three ways:
In this case, encode the image content as base64 and pass it via this parameter. If the user mentions an uploaded image but does not provide a path, URL, or base64 data, ask the user for the local absolute path. Prompt must be in English. If the user provides Chinese or other non-English text, translate it to English before calling this tool.
BEFORE YOU INSTALL
4 tools when we connected; the project documents 9. The missing five are enhance_image_sync, colorize_image_sync, denoise_image_sync and two status pollers; the README lists all nine and names no flag or plan that hides them.
Both documented clients run the server on your machine.
INSTALLATION
npm install -g @avclabs.ai/media-mcp{
"mcpServers": {
"video-enhancement": {
"command": "npx",
"args": [
"-y",
"@avclabs.ai/media-mcp@latest"
],
"env": {
"API_KEY": "<YOUR_API_KEY>"
}
}
}
}MCP servers
transloadit
maoxiaoke
soundside-design
TSavo