Avc Test Py Mcp

io.github.z416479660Published by GitHub account z416479660v1.0.0Updated Oct 27, 2026

MCP server for video enhancement (create_task, get_task_status, enhance_video_sync)

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

MCP server that lets an assistant submit video enhancement jobs to a remote FastAPI service, poll their status, and retrieve enhanced video links.

What you can do
  • Create enhancement tasks from a video URL or a local file path, with a target resolution such as 480p up to 2k
  • Check a task's status, progress, resulting video URL and error message by task ID
  • Run an enhancement synchronously, polling at a set interval until it finishes or a timeout is reached
  • Upload local video files to the enhancement service, up to 100MB per file
When to use it
Useful when you want an assistant to upscale or enhance video files or URLs through a hosted service and get back a link to the processed result, either as a background task or a blocking call.
Requirements
Runs as a local process installed from PyPI (pip or uv) or npm, configured in a desktop client such as Claude Desktop. Needs the HTTP_API_BASE_URL setting (defaults to the provider's service) and the required HTTP_API_KEY secret, passed as a command-line argument or environment variable. Network access to the enhancement service is required.
Before you install
Requires an API key (HTTP_API_KEY) for the remote service; keep it out of shared config files. Local files selected with type "local" are read, base64-encoded and uploaded to the third-party enhancement service, so avoid sensitive media. Jobs may consume paid service quota, and the synchronous tool blocks until completion or timeout.

Installation

In SourceWeft

  1. Open Avc Test Py 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

avc-test-py-mcp (Python)

[PyPI version] [Python 3.10+] [License: MIT]

基于 MCP 协议的视频增强服务，作为 MCP Client-Server 与 FastAPI HTTP Server 交互。

功能

提供以下 MCP Tools：

  • create_task - 创建视频增强任务（支持 URL 或本地文件上传）
  • get_task_status - 查询任务状态
  • enhance_video_sync - 同步增强视频（阻塞等待）

安装

从 PyPI 安装（推荐）

bash
# 使用 pip 安装pip install avc-test-py-mcp
# 或使用 uv 安装uv pip install avc-test-py-mcp

从源码安装

bash
git clone https://github.com/yourusername/avc-test-py-mcp.gitcd python_client
# 使用 uv 安装（推荐）uv pip install -e ".[dev]"
# 或使用 pip 安装pip install -e ".[dev]"

使用方法

1. 命令行启动

bash
# 直接运行（安装后）avc-test-py-mcp --base-url https://mcp.luluhero.com --api-key your-api-key
# 或使用环境变量export HTTP_API_BASE_URL=https://mcp.luluhero.comexport HTTP_API_KEY=your-api-keyavc-test-py-mcp

2. 在 Claude Desktop 中配置

编辑 Claude Desktop 配置文件：

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%/Claude/claude_desktop_config.json

json
{  "mcpServers": {    "video-enhancement": {      "command": "avc-test-py-mcp",      "args": [        "--base-url",        "https://mcp.luluhero.com",        "--api-key",        "your-api-key"      ]    }  }}

3. 使用 uv run 运行（开发模式）

bash
uv run avc-test-py-mcp --base-url https://mcp.luluhero.com --api-key your-api-key

提供的 Tools

create_task

创建视频增强任务（异步）。

参数：

  • video_source (string, required): 视频 URL 或本地文件路径
  • type (string, optional): 上传类型，默认 "url"
    • 可选值: "url" - 网络视频URL, "local" - 本地文件路径
  • resolution (string, optional): 目标分辨率，默认 720p
    • 可选值: 480p, 540p, 720p, 1080p, 2k

使用示例：

python
# URL 方式{  "video_source": "https://example.com/video.mp4",  "type": "url",  "resolution": "1080p"}
# 本地文件方式{  "video_source": "/path/to/local/video.mp4",  "type": "local",  "resolution": "1080p"}

返回值：

json
{  "success": true,  "task_id": "xxx",  "status": "wait"}

get_task_status

查询任务状态。

参数：

  • task_id (string, required): 任务ID

使用示例：

python
{  "task_id": "task-123-abc"}

返回值：

json
{  "success": true,  "task_id": "xxx",  "status": "completed",  "progress": 100,  "video_url": "https://...",  "error_message": null,  "created_at": "2024-01-01T00:00:00Z",  "updated_at": "2024-01-01T00:01:00Z"}

enhance_video_sync

同步增强视频（阻塞等待完成）。

参数：

  • video_source (string, required): 视频 URL 或本地文件路径
  • type (string, optional): 上传类型，默认 "url"
    • 可选值: "url" - 网络视频URL, "local" - 本地文件路径
  • resolution (string, optional): 目标分辨率，默认 720p
  • poll_interval (number, optional): 轮询间隔（秒），默认 5
  • timeout (number, optional): 超时时间（秒），默认 600

使用示例：

python
{  "video_source": "https://example.com/video.mp4",  "type": "url",  "resolution": "1080p",  "poll_interval": 5,  "timeout": 600}

返回值：

json
{  "success": true,  "task_id": "xxx",  "status": "completed",  "progress": 100,  "video_url": "https://..."}

文件上传说明

当 type 设置为 "local" 时，MCP Server 会：

  1. 读取本地文件
  2. 将文件转为 base64 编码
  3. 上传到视频增强服务

限制：

  • 最大文件大小：100MB

环境变量

变量名说明默认值
HTTP_API_BASE_URLFastAPI HTTP Server 地址https://mcp.luluhero.com
HTTP_API_KEYAPI 认证密钥无

开发

bash
# 克隆仓库git clone https://github.com/yourusername/avc-test-py-mcp.gitcd python_client
# 安装开发依赖uv pip install -e ".[dev]"
# 运行测试pytest
# 代码格式化ruff format .ruff check --fix .

发布到 PyPI

bash
# 安装构建工具uv pip install build twine
# 构建分发包python -m build
# 上传到 PyPI（测试）python -m twine upload --repository testpypi dist/*
# 上传到 PyPI（正式）python -m twine upload dist/*

License

MIT License - 详见 LICENSE 文件

Source: README.md at commit e569a16

Tools

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

Version history

1
  1. v1.0.0LatestSep 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