Media MCP

MCP Server for video enhancement and image segmentation (SAM3)

Connector by avclabs · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/avclabs-media-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

MCP Server for video enhancement and image segmentation (SAM3)

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 4 read · 4 write · 1 delete
Secrets: 1 (API keys, tokens or passwords)
Install scripts: Not scanned yet
Runs as: Node.js package

Tools by what they do 9

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

get_image_task_status
get_sam3_task_status
get_task_status
sam3_predict

Write 4 · Create, change, send or run things.

colorize_image_sync
create_task
enhance_image_sync
enhance_video_sync

Delete 1 · Delete, drop, revoke or wipe things.

denoise_image_sync

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

API_KEY

Tools (9)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

colorize_image_sync
Colorize a black-and-white photo (黑白照片上色/旧照片上色). Use this tool ONLY for adding color to grayscale or black-and-white images. Two upload methods are supported: 1. URL upload: provide an image URL 2. Local upload: provide a local file path, the MCP Server will auto-upload to TOS object storage Best for images with estimated processing time < 1 minute. If the task is not completed within the timeout, the tool returns early with a task_id. Use get_image_task_status to continue polling.
create_task
Create a video enhancement task (asynchronous). Two upload methods are supported: 1. URL upload: provide a video URL 2. Local upload: provide a local file path, the MCP Server will auto-upload to TOS object storage Parameters: - video_source: video URL or local file path - type: "url" or "local" - resolution: target resolution After creating a task, a task_id is returned immediately. Use get_task_status to poll for results until status becomes "completed" or "failed".
denoise_image_sync
Remove noise from an image (图片降噪/去噪). Use this tool ONLY for denoising noisy or grainy images. Two upload methods are supported: 1. URL upload: provide an image URL 2. Local upload: provide a local file path, the MCP Server will auto-upload to TOS object storage Best for images with estimated processing time < 1 minute. If the task is not completed within the timeout, the tool returns early with a task_id. Use get_image_task_status to continue polling.
enhance_image_sync
Enhance/upscale an image to improve quality (图片增强/放大/超分辨率). Use this tool ONLY for image enhancement and upscaling tasks. Two upload methods are supported: 1. URL upload: provide an image URL 2. Local upload: provide a local file path, the MCP Server will auto-upload to TOS object storage Best for images with estimated processing time < 1 minute. If the task is not completed within the timeout, the tool returns early with a task_id. Use get_image_task_status to continue polling.
enhance_video_sync
Synchronously enhance video (blocks until completion). Two upload methods are supported: 1. URL upload: provide a video URL 2. Local upload: provide a local file path, the MCP Server will auto-upload to TOS object storage Parameters: - video_source: video URL or local file path - type: "url" or "local" - resolution: target resolution - poll_interval: polling interval in seconds - timeout: synchronous wait timeout in seconds, default 45 Best for short videos (estimated processing time < 1 minute). If the task is not completed within the timeout, the tool returns early with a task_id. Use get…
get_image_task_status
Query image processing 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.
get_sam3_task_status
Query SAM3 image segmentation task status by task_id. Status can be: processing, completed, or failed. If completed, the result URL is returned.
get_task_status
Query 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_predict
Analyze an image using the SAM3 segmentation API to generate inference results (masks, boxes, scores). The image can be provided in one of three ways: 1. imagePath: Absolute path of a local image file (e.g. C:\Users\xxx\photo.png). Use this when the user provides a local file path. 2. imageUrl: Publicly accessible URL of the image (e.g. https://example.com/photo.jpg). Use this when the user provides a web link. 3. imageBase64: Base64-encoded image data. Use this when the user uploads or drags-and-drops an image as an attachment and no local path is available. In this case, encode the image con…

Signals

Stars: 0
Forks: 0
Open issues: 1
Weekly downloads: 35
Last commit: Oct 17, 2026 (11 days ago)
Last release: May 12, 2026 (5 months ago)
Last package publish: Oct 13, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.avclabs/media-mcp
Version: 0.2.0
Auth: API key
Packages: npm @avclabs.ai/media-mcp
License: MIT
Repository: github.com/avclabs/media-mcp
First seen: Oct 24, 2026
Last checked: Oct 25, 2026
Source: Official MCP Registry github-graphql