avclabs MCP

@avclabs.ai/media-mcp

Node.js >=18 · MIT License

Video Enhancement

The following MCP Tools are provided:

<>create_taskCreate a video enhancement task (supports URL or local file upload)

Create a video enhancement task (async).

Parameter

ParameterTypeRequiredDefaultDescription
video_sourcestringYes-Video URL or local file path
typestringNourlUpload type: url / local
resolutionstringNo720pTarget resolution: 480p, 540p, 720p, 1080p, 2k

Request Example

json
{
  "video_source": "https://example.com/video.mp4",
  "type": "url",
  "resolution": "1080p"
}

Response Example

json
{
  "success": true,
  "task_id": "xxx",
  "status": "processing"
}
<>get_task_statusQuery task status

Query video enhancement task status. The status field in the return value may be: processing, completed, or failed. If status is processing, you need to wait a few seconds and call this tool again to poll.

Parameter

ParameterTypeRequiredDescription
task_idstringYesTask ID

Returns:

json
{
  "success": true,
  "task_id": "xxx",
  "status": "completed",
  "progress": 100,
  "video_url": "https://...",
  "message": "任务仍在处理中,请稍后再查询"
}
<>enhance_video_syncSynchronously enhance video (block until completion, default 50s truncation)

Synchronously enhance video (block until completion). Only suitable for short videos (estimated processing time < 1 minute). If the task is not completed within 50 seconds, the tool will return early and include task_id. You need to use get_task_status to continue querying.

Parameter

ParameterTypeRequiredDefaultDescription
video_sourcestringYes-Video URL or local file path
typestringNourlUpload type: url / local
resolutionstringNo720pTarget resolution: 480p, 540p, 720p, 1080p, 2k
poll_intervalnumberNo5Polling interval (seconds)
timeoutnumberNo50Synchronous wait timeout (seconds), returns early after exceeding

Request Example

json
{
  "video_source": "https://example.com/video.mp4",
  "type": "url",
  "resolution": "1080p",
  "poll_interval": 5,
  "timeout": 50
}

Truncated return example (not completed within 50s)

json
{
  "success": true,
  "status": "processing",
  "task_id": "xxx",
  "message": "任务仍在处理中(已等待 50 秒)。请使用 get_task_status 工具继续查询此任务状态。",
  "note": "此工具对长任务的同步等待已被截断,请切换到 get_task_status 轮询模式。"
}

Image Segmentation (SAM3) → sam3_predict

avclabs

AI video enhancement service platform based on the MCP protocol, providing developers with powerful video processing capabilities.

© 2026 AVCLabs Inc. All Rights Reserved.