Skip to main content
Glama
deenesjakoruzh
avclabs

@avclabs.ai/enhance-mcp

Official
by avclabs
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
JavaScript
Hybrid

@avclabs.ai/enhance-mcp (Node.js)

npm version Node.js >=18 License: MIT

中文文档 | Inglés

Un servicio de mejora de vídeo basado en el protocolo MCP, que actúa como cliente-servidor MCP para interactuar con un servidor HTTP FastAPI.

Características

Se proporcionan las siguientes herramientas MCP:

  • create_task - Crear una tarea de mejora de vídeo (admite URL o carga de archivo local)

  • get_task_status - Consultar el estado de la tarea

  • enhance_video_sync - Mejorar un vídeo de forma síncrona (espera bloqueante)

Instalación

Instalar desde npm (Recomendado)

npm install -g @avclabs.ai/enhance-mcp

O utilice yarn/pnpm:

yarn global add @avclabs.ai/enhance-mcp
pnpm add -g @avclabs.ai/enhance-mcp

Instalar desde el código fuente

git clone https://github.com/avclabs/enhance-mcp.git
cd js_client
npm install
npm run build

Uso

1. Línea de comandos

Utilícelo directamente después de la instalación global:

avclabs-enhance-mcp --base-url https://mcp.avc.ai --api-key your-api-key

O utilice variables de entorno:

# 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. Configurar en Claude Desktop

Edite el archivo de configuración de Claude Desktop:

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. Usar con npx (No requiere instalación global)

npx @avclabs.ai/enhance-mcp --base-url https://mcp.avc.ai --api-key your-api-key

Configuración de Claude Desktop:

{
  "mcpServers": {
    "video-enhancement": {
      "command": "npx",
      "args": [
        "@avclabs.ai/enhance-mcp",
        "--base-url",
        "https://mcp.avc.ai",
        "--api-key",
        "your-api-key"
      ]
    }
  }
}

Herramientas proporcionadas

create_task

Crear una tarea de mejora de vídeo (asíncrona).

Parámetros:

  • video_source (string, requerido): URL del vídeo o ruta del archivo local

  • type (string, opcional): Tipo de carga, por defecto es "url"

    • Opciones: "url" - URL de vídeo de red, "local" - Ruta de archivo local

  • resolution (string, opcional): Resolución objetivo, por defecto es 720p

    • Opciones: 480p, 540p, 720p, 1080p, 2k

Ejemplo:

// 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"
}

Retorno:

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

get_task_status

Consultar el estado de la tarea.

Parámetros:

  • task_id (string, requerido): ID de la tarea

Ejemplo:

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

Retorno:

{
  "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

Mejorar un vídeo de forma síncrona (espera bloqueante hasta completar).

Parámetros:

  • video_source (string, requerido): URL del vídeo o ruta del archivo local

  • type (string, opcional): Tipo de carga, por defecto es "url"

    • Opciones: "url" - URL de vídeo de red, "local" - Ruta de archivo local

  • resolution (string, opcional): Resolución objetivo, por defecto es 720p

  • poll_interval (number, opcional): Intervalo de sondeo en segundos, por defecto es 5

  • timeout (number, opcional): Tiempo de espera en segundos, por defecto es 600

Ejemplo:

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

Retorno:

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

Notas sobre la carga de archivos

Cuando type se establece en "local", el servidor MCP hará lo siguiente:

  1. Leerá el archivo local

  2. Codificará el archivo en base64

  3. Lo subirá al servicio de mejora de vídeo

Limitaciones:

  • Tamaño máximo de archivo: 100MB

Variables de entorno

Variable

Descripción

Por defecto

HTTP_API_BASE_URL

Dirección del servidor HTTP FastAPI

https://mcp.avc.ai

HTTP_API_KEY

Clave de autenticación de API

Ninguna

Desarrollo

# 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

Licencia

Licencia MIT - Consulte el archivo LICENSE para más detalles.

Available Tools

3 tools
create_taskB

创建视频增强任务（异步）

支持两种上传方式：

  1. URL 上传：提供视频 URL

  2. 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

ParametersJSON Schema
NameRequiredDescriptionDefault
video_sourceYes视频URL地址或本地文件路径
typeNo上传类型：url=网络视频，local=本地文件url
resolutionNo目标分辨率，默认720p720p

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It notes the task is async, but fails to mention authentication needs, rate limits, or the return format (e.g., task ID). It also does not disclose any side effects or failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description uses bullet points and is relatively concise. Each paragraph serves a purpose, though some wording could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the async nature and upload methods, but it lacks return value details (no output schema) and does not mention error cases or post-creation steps. Given the tool's complexity, it is minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description adds value by explaining that local files are automatically uploaded to TOS storage, which is not in the schema. It also summarizes parameter meanings clearly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates an asynchronous video enhancement task and lists two upload methods. It implicitly differentiates from the sibling 'enhance_video_sync' which is synchronous, but does not explicitly name the sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the two upload methods and parameter defaults, but does not provide explicit guidance on when to use this tool versus siblings, nor does it state prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

enhance_video_syncA

同步增强视频（阻塞等待完成）

支持两种上传方式：

  1. URL 上传：提供视频 URL

  2. 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）

ParametersJSON Schema
NameRequiredDescriptionDefault
video_sourceYes视频URL地址或本地文件路径
typeNo上传类型：url=网络视频，local=本地文件url
resolutionNo目标分辨率，默认720p720p
poll_intervalNo轮询间隔（秒），默认5
timeoutNo超时时间（秒），默认600

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses blocking behavior and automatic upload to TOS for local files, but lacks details on error handling, side effects, or required permissions. Without annotations, the description carries the full burden but still provides moderate transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a clear front-loaded purpose and well-structured bullet points for parameters. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers all 5 parameters, behavior (blocking), and upload methods. It omits expected return value and prerequisites, but given the lack of output schema, it is sufficiently complete for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. The description adds value by grouping parameters and explaining the two upload methods, which goes beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool synchronously enhances video and blocks until completion. It distinguishes itself from siblings like create_task and get_task_status by focusing specifically on video enhancement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly guide when to use this tool over alternatives, nor does it mention when not to use it. However, the context of video enhancement is clear, and the sibling tools handle different tasks, so usage is implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_task_statusA

查询视频增强任务状态

ParametersJSON Schema
NameRequiredDescriptionDefault
task_idYes任务ID

TDQS

A3.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and the description only states the purpose without disclosing any behavioral traits such as polling requirements, rate limits, or expected response behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no wasted words; efficient and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple status query with one parameter, the description is mostly complete but could benefit from mentioning possible return statuses or output format since no output schema is provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description adds no additional meaning beyond what is already in the input schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'query' and the resource 'video enhancement task status', distinguishing from sibling tools 'create_task' and 'enhance_video_sync' which have different actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives, but the context of sibling tools implies it is for checking status after creation or enhancement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.18
    • First observedcreate_task
    • First observedenhance_video_sync
    • First observedget_task_status
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a distinct purpose: creating an async task, performing a synchronous enhancement, and querying task status. No overlap or ambiguity.

Naming Consistency4/5

All names use snake_case and verb_noun pattern, but the verbs vary (create, enhance, get) and 'enhance_video_sync' mixes a descriptor. Mostly consistent.

Tool Count4/5

Three tools is on the lower end but reasonable for a focused video enhancement service. Each tool serves a clear function without being redundant.

Completeness3/5

Covers creation and status checking, but lacks cancellation, listing all tasks, or retrieving final results explicitly. Minor but notable gaps.

Maintenance

ActivityNo data
ResponsivenessSyncing

Resources

Related MCP Connectors