Media Mcp

io.github.avclabsPublished by GitHub account avclabsv0.2.0Updated Oct 24, 2026

MCP Server for video enhancement and image segmentation (SAM3)

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

AVCLabs media MCP server that lets an assistant enhance videos and images and run SAM3 image segmentation through hosted AVCLabs services.

What you can do
  • Enhance videos: create enhancement tasks, check task status, and run a synchronous enhancement call
  • Enhance images: synchronous enhancement, colorization and denoising, plus image task status checks
  • Segment images with SAM3: run predictions and poll SAM3 task status
  • The all-in-one package bundles all nine tools; separate per-function packages expose only video, image or SAM3 tools
When to use it
Use it when you want an assistant to upscale or enhance video, colorize or denoise images, or produce SAM3 segmentation masks, and you are willing to send media to AVCLabs' hosted services.
Requirements
Runs locally as a stdio process, typically launched with npx, so Node.js and npm are needed. Requires an API_KEY environment variable for the video enhancement and SAM3 services. Network access to the AVCLabs production hosts is required. Desktop only; not executable in a web client.
Before you install
The API_KEY is a secret passed in the environment and should not be shared or committed. Media files are uploaded to AVCLabs' hosted services for processing, so avoid sending confidential content. Tasks are created on a paid third-party service, so usage may incur costs. The all-in-one package loads all nine tool definitions into the session.

Installation

In SourceWeft

  1. Open Media Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

media-mcp monorepo

English | 中文

[Node.js >=18] [License: MIT]

MCP servers wrapping the AVCLabs hosted media services, published as one function per npm package so an MCP client session only loads the tool definitions it actually uses.

Packages

PackageFunctionToolsBin
@avclabs.ai/video-mcpVideo enhancementcreate_task, get_task_status, enhance_video_syncvideo-mcp
@avclabs.ai/image-mcpImage enhancement / colorization / denoisingenhance_image_sync, colorize_image_sync, denoise_image_sync, get_image_task_statusimage-mcp
@avclabs.ai/sam3-mcpSAM3 image segmentationsam3_predict, get_sam3_task_statussam3-mcp
@avclabs.ai/media-mcpLegacy all-in-one (all 9 tools)everything abovemedia-mcp
@avclabs.ai/media-mcp-coreShared internal library (not an MCP server)——

Why one function per package

  • Smaller context: MCP clients inject every tool definition (name, description, JSON schema) of each configured server into the session. A client that only needs image tools no longer pays for video and SAM3 definitions.
  • Less tool ambiguity: with a single get_*_task_status variant present, the model picks tools more reliably.
  • Independent enablement: expose exactly one function per client or per audience (e.g. SAM3 only for the annotation team).

The legacy all-in-one @avclabs.ai/media-mcp keeps working unchanged for existing configurations; see its README for a migration note.

Quick start

Every server is a stdio MCP server over npx. For example, image tools only:

json
{  "mcpServers": {    "image-mcp": {      "command": "npx",      "args": ["-y", "-p", "@avclabs.ai/image-mcp@latest", "image-mcp"],      "env": { "API_KEY": "your-api-key" }    }  }}

Each package ships exactly one bin named like the package, so plain npx -y <package> also works; the snippets use the explicit -p <package> <bin> form because it pins the exact binary regardless of how a package's bin set evolves. Each package README (video, image, SAM3) has full install instructions for Claude Code, Cursor, and global installs, plus the configuration variables it reads.

All packages share one API_KEY and the same production host defaults (https://mcp.avc.ai/enhance and https://mcp.avc.ai/sam).

Repository layout

packages/  core/       shared library: tool registration, polling, TOS upload, config  video-mcp/  video enhancement server (3 tools)  image-mcp/  image processing server (4 tools)  sam3-mcp/   SAM3 segmentation server (2 tools)  media-mcp/  legacy all-in-one server (9 tools)

Domain vocabulary shared across the packages lives in CONTEXT.md; decisions are recorded in docs/adr/.

Development and release

bash
npm ci               # installs workspaces and builds every packagenpm test             # rebuild + run all package testsnpm run release:verify   # metadata gate + audit + tests + pack dry-runnode scripts/e2e-check.mjs  # stdio E2E for all four server entries

To iterate on one package: build core once (npm run build -w packages/core), then run npm run dev -w packages/<pkg> (tsc --watch) in another terminal.

Maintainers: see the release guide for publish order (core first), versioning, tags, and smoke tests. Publishing is manual from a clean checkout; the CI workflow runs the same verification gate on Node 22.

License

MIT License — see LICENSE.

Source: README.md at commit 584c4b8

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts