@avclabs.ai/enhance-mcp
Enables video enhancement through MCP tools for creating tasks, querying status, and synchronous enhancement, supporting URL or local file inputs.
README
@avclabs.ai/enhance-mcp (Node.js)
中文文档 | English
A video enhancement service based on the MCP protocol, acting as an MCP Client-Server to interact with a FastAPI HTTP Server.
Features
The following MCP Tools are provided:
create_task- Create a video enhancement task (supports URL or local file upload)get_task_status- Query task statusenhance_video_sync- Synchronously enhance a video (blocking wait)
Installation
Install from npm (Recommended)
npm install -g @avclabs.ai/enhance-mcp
Or use yarn/pnpm:
yarn global add @avclabs.ai/enhance-mcp
pnpm add -g @avclabs.ai/enhance-mcp
Install from Source
git clone https://github.com/avclabs/enhance-mcp.git
cd js_client
npm install
npm run build
Usage
1. Command Line
Use directly after global installation:
avclabs-enhance-mcp --base-url https://mcp.avc.ai --api-key your-api-key
Or use environment variables:
# Windows PowerShell
$env:HTTP_API_BASE_URL="https://mcp.avc.ai"
$env:HTTP_API_KEY="your-api-key"
avclabs-enhance-mcp
# Windows CMD
set HTTP_API_BASE_URL=https://mcp.avc.ai
set HTTP_API_KEY=your-api-key
avclabs-enhance-mcp
# macOS/Linux
export HTTP_API_BASE_URL=https://mcp.avc.ai
export HTTP_API_KEY=your-api-key
avclabs-enhance-mcp
2. Configure in Claude Desktop
Edit the Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"video-enhancement": {
"command": "avclabs-enhance-mcp",
"args": [
"--base-url",
"https://mcp.avc.ai",
"--api-key",
"your-api-key"
]
}
}
}
3. Use with npx (No Global Installation Required)
npx @avclabs.ai/enhance-mcp --base-url https://mcp.avc.ai --api-key your-api-key
Claude Desktop configuration:
{
"mcpServers": {
"video-enhancement": {
"command": "npx",
"args": [
"@avclabs.ai/enhance-mcp",
"--base-url",
"https://mcp.avc.ai",
"--api-key",
"your-api-key"
]
}
}
}
Provided Tools
create_task
Create a video enhancement task (asynchronous).
Parameters:
video_source(string, required): Video URL or local file pathtype(string, optional): Upload type, defaults to "url"- Options:
"url"- Network video URL,"local"- Local file path
- Options:
resolution(string, optional): Target resolution, defaults to 720p- Options: 480p, 540p, 720p, 1080p, 2k
Example:
// URL mode
{
"video_source": "https://example.com/video.mp4",
"type": "url",
"resolution": "1080p"
}
// Local file mode
{
"video_source": "/path/to/local/video.mp4",
"type": "local",
"resolution": "1080p"
}
Returns:
{
"success": true,
"task_id": "xxx",
"status": "wait"
}
get_task_status
Query task status.
Parameters:
task_id(string, required): Task ID
Example:
{
"task_id": "task-123-abc"
}
Returns:
{
"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
Synchronously enhance a video (blocking wait until completion).
Parameters:
video_source(string, required): Video URL or local file pathtype(string, optional): Upload type, defaults to "url"- Options:
"url"- Network video URL,"local"- Local file path
- Options:
resolution(string, optional): Target resolution, defaults to 720ppoll_interval(number, optional): Polling interval in seconds, defaults to 5timeout(number, optional): Timeout in seconds, defaults to 600
Example:
{
"video_source": "https://example.com/video.mp4",
"type": "url",
"resolution": "1080p",
"poll_interval": 5,
"timeout": 600
}
Returns:
{
"success": true,
"task_id": "xxx",
"status": "completed",
"progress": 100,
"video_url": "https://..."
}
File Upload Notes
When type is set to "local", the MCP Server will:
- Read the local file
- Encode the file as base64
- Upload it to the video enhancement service
Limitations:
- Maximum file size: 100MB
Environment Variables
| Variable | Description | Default |
|---|---|---|
HTTP_API_BASE_URL |
FastAPI HTTP Server address | https://mcp.avc.ai |
HTTP_API_KEY |
API authentication key | None |
Development
# Clone the repository
git clone https://github.com/avclabs/enhance-mcp.git
cd js_client
# Install dependencies
npm install
# Development mode (auto-compile)
npm run dev
# Build
npm run build
License
MIT License - See LICENSE file for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。