media-mcp
Officialmedia-mcp monorepo
English | 中文
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
Package | Function | Tools | Bin |
Video enhancement |
|
| |
Image enhancement / colorization / denoising |
|
| |
SAM3 image segmentation |
|
| |
Legacy all-in-one (all 9 tools) | everything above |
| |
Shared internal library (not an MCP server) | — | — |
Related MCP server: Grok Imagine Video 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_statusvariant 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:
{
"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
npm ci # installs workspaces and builds every package
npm test # rebuild + run all package tests
npm run release:verify # metadata gate + audit + tests + pack dry-run
node scripts/e2e-check.mjs # stdio E2E for all four server entriesTo 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.
Available Tools
4 toolscreate_taskB
创建视频增强任务(异步)
支持两种上传方式:
URL 上传:提供视频 URL
本地上传:提供本地文件路径,MCP Server 自动上传到 TOS 对象存储
参数说明:
video_source: 视频 URL 或本地文件路径
type: "url" 或 "local"
resolution: 目标分辨率
Inputs: video_source (required), type, resolution.
enhance_video_syncA
同步增强视频(阻塞等待完成)
支持两种上传方式:
URL 上传:提供视频 URL
本地上传:提供本地文件路径,MCP Server 自动上传到 TOS 对象存储
参数说明:
video_source: 视频 URL 或本地文件路径
type: "url" 或 "local"
resolution: 目标分辨率
poll_interval: 轮询间隔(秒)
timeout: 超时时间(秒)
Inputs: video_source (required), type, resolution, poll_interval, +1 more.
get_task_statusA
查询视频增强任务状态
Inputs: task_id (required).
sam3_predictA
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:
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.
imageUrl: Publicly accessible URL of the image (e.g. https://example.com/photo.jpg). Use this when the user provides a web link.
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 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.
Inputs: prompt (required), imagePath, imageUrl, imageBase64.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The first three tools are about video enhancement tasks with overlapping functionality (create_task and enhance_video_sync both appear to initiate enhancement), and the fourth tool (sam3_predict) is for image segmentation, a completely different domain. The descriptions are not clear enough to distinguish which tool to use for a given task, causing confusion.
Tool names partially follow a verb_noun pattern (create_task, get_task_status), but 'enhance_video_sync' is awkward and 'sam3_predict' mixes model name with verb, introducing inconsistency.
With 4 tools, the count is reasonable for a focused server, but the server actually combines two unrelated capabilities (video enhancement and image segmentation), making the scope unclear but the number itself is not extreme.
For video enhancement, there are create, sync enhance, and status query, but missing cancel, list, or delete operations. For image segmentation, only a single predict tool exists. The surface is incomplete for both domains.
Maintenance
Related MCP Connectors
MCP server for Wan AI video generation
MCP server for Google Veo AI video generation
MCP server for MiniMax H3 multimodal video generation
MCP server for Luma Dream Machine AI video generation
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server for 4K video generation using Google VEO 3.1 — text-to-video, image-to-video, video extension, and frame interpolation.3MIT
- AlicenseAqualityCmaintenanceMCP server for generating, editing, and batch processing videos using xAI's Grok Imagine Video API, with support for text-to-video, image-to-video, and video editing via natural language prompts.4105 npm1MIT
- AlicenseAqualityDmaintenanceMCP server for AI-powered media generation: images, videos, audio, and upscaling using 99 AI models.6MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server enabling video processing via natural language: transcription with Whisper, segment cutting with FFmpeg, and file management.MIT