Skip to main content
Glama
kamelirzouni

Qwen Max MCP Server

by kamelirzouni

Servidor MCP Qwen Max

Una implementación de servidor de Protocolo de Contexto de Modelo (MCP) para el modelo de lenguaje Qwen Max.

insignia de herrería

¿Por qué Node.js? Esta implementación utiliza Node.js/TypeScript, ya que actualmente ofrece la integración más estable y fiable con servidores MCP en comparación con otros lenguajes como Python. El SDK de Node.js para MCP ofrece mayor seguridad de tipos, gestión de errores y compatibilidad con Claude Desktop.

Prerrequisitos

  • Node.js (v18 o superior)

  • npm

  • Escritorio de Claude

  • Clave API de Dashscope

Related MCP server: DeepSeek MCP Server

Instalación

Instalación mediante herrería

Para instalar Qwen Max MCP Server para Claude Desktop automáticamente a través de Smithery :

npx -y @smithery/cli install @66julienmartin/mcp-server-qwen_max --client claude

Instalación manual

git clone https://github.com/66julienmartin/mcp-server-qwen-max.git
cd Qwen_Max
npm install

Selección de modelos

Este servidor utiliza el modelo Qwen-Max de forma predeterminada. La serie Qwen ofrece varios modelos comerciales con diferentes capacidades:

Qwen-Max

Proporciona el mejor rendimiento de inferencia, especialmente para tareas complejas y de varios pasos.

Ventana de contexto: 32.768 tokens

  • Entrada máxima: 30,720 tokens

  • Salida máxima: 8,192 tokens

  • Precios: $0,0016/1000 tokens (entrada), $0,0064/1000 tokens (salida)

  • Cuota gratuita: 1 millón de tokens

Versiones disponibles:

  • qwen-max (Estable)

  • qwen-max-latest (Último)

  • qwen-max-2025-01-25 (Instantánea, también conocida como qwen-max-0125 o Qwen2.5-Max)

Qwen-Plus

Combinación equilibrada de rendimiento, velocidad y costo, ideal para tareas moderadamente complejas.

Ventana de contexto: 131.072 tokens

  • Entrada máxima: 129,024 tokens

  • Salida máxima: 8,192 tokens

  • Precios: $0,0004/1000 tokens (entrada), $0,0012/1000 tokens (salida)

  • Cuota gratuita: 1 millón de tokens

Versiones disponibles:

  • qwen-plus (Estable)

  • qwen-plus-latest (Último)

  • qwen-plus-2025-01-25 (Instantánea, también conocida como qwen-plus-0125)

Qwen-Turbo

Rápida velocidad y bajo costo, adecuado para tareas sencillas.

  • Ventana de contexto: 1.000.000 tokens

  • Entrada máxima: 1.000.000 tokens

  • Salida máxima: 8,192 tokens

  • Precios: $0,00005/1000 tokens (entrada), $0,0002/1000 tokens (salida)

  • Cuota gratuita: 1 millón de tokens

Versiones disponibles:

  • qwen-turbo (Estable)

  • qwen-turbo-latest (Último)

  • qwen-turbo-2024-11-01 (Instantánea, también conocida como qwen-turbo-1101)

Para modificar el modelo, actualice el nombre del modelo en src/index.ts:

// For Qwen-Max (default)
model: "qwen-max"

// For Qwen-Plus
model: "qwen-plus"

// For Qwen-Turbo
model: "qwen-turbo"

Para obtener información más detallada sobre los modelos disponibles, visita la Documentación del modelo de Alibaba Cloud https://www.alibabacloud.com/help/en/model-studio/getting-started/models?spm=a3c0i.23458820.2359477120.1.446c7d3f9LT0FY .

Estructura del proyecto

qwen-max-mcp/
├── src/
│   ├── index.ts             # Main server implementation
├── build/                   # Compiled files
│   ├── index.js
├── LICENSE
├── README.md
├── package.json
├── package-lock.json
└── tsconfig.json

Configuración

  1. Cree un archivo .env en la raíz del proyecto:

DASHSCOPE_API_KEY=your-api-key-here
  1. Actualizar la configuración de Claude Desktop:

{
  "mcpServers": {
    "qwen_max": {
      "command": "node",
      "args": ["/path/to/Qwen_Max/build/index.js"],
      "env": {
        "DASHSCOPE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Desarrollo

npm run dev     # Watch mode
npm run build   # Build
npm run start   # Start server

Características

  • Generación de texto con modelos Qwen

  • Parámetros configurables (max_tokens, temperatura)

  • Manejo de errores

  • Compatibilidad con el protocolo MCP

  • Integración de Claude Desktop

  • Soporte para todos los modelos comerciales de Qwen (Max, Plus, Turbo)

  • Amplias ventanas de contexto de token

Uso de la API

// Example tool call
{
  "name": "qwen_max",
  "arguments": {
    "prompt": "Your prompt here",
    "max_tokens": 8192,
    "temperature": 0.7
  }
}

El parámetro de temperatura

El parámetro de temperatura controla la aleatoriedad de la salida del modelo:

Valores más bajos (0,0-0,7): Resultados más centrados y deterministas. Valores más altos (0,7-1,0): Resultados más creativos y variados.

Configuraciones de temperatura recomendadas por tarea:

Generación de código: 0,0-0,3 Redacción técnica: 0,3-0,5 Tareas generales: 0,7 (predeterminado) Redacción creativa: 0,8-1,0

Manejo de errores

El servidor proporciona mensajes de error detallados para problemas comunes:

Errores de autenticación de API Parámetros no válidos Limitación de velocidad Problemas de red Límite de token excedido Problemas de disponibilidad del modelo

Contribuyendo

¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios.

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

1 tool
qwen_maxC

Generate text using Qwen Max model

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesThe text prompt to generate content from
max_tokensNoMaximum number of tokens to generate
temperatureNoSampling temperature (0-2)

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. While 'Generate text' implies a read-only operation, it doesn't disclose important behavioral traits like rate limits, authentication requirements, response format, error conditions, or cost implications. For a text generation tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.

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 extremely concise at just 5 words. Every word earns its place by specifying the action ('Generate'), resource ('text'), and model ('Qwen Max model'). There's no wasted language, repetition, or unnecessary elaboration. The structure is front-loaded with the core function.

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

Completeness2/5

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

Given this is a text generation tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns, error conditions, rate limits, or any behavioral characteristics. While the schema covers parameters well, the overall context for using this tool effectively is incomplete. A text generation tool needs more contextual information than 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%, so all parameters are documented in the schema. The description adds no parameter-specific information beyond what the schema already provides. It doesn't explain relationships between parameters, provide examples, or add semantic context. The baseline score of 3 reflects adequate parameter documentation coming entirely from the schema.

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's purpose as 'Generate text using Qwen Max model' - a specific verb ('Generate') with resource ('text') and model specification. It distinguishes itself as a text generation tool, though with no sibling tools, differentiation isn't needed. The purpose is unambiguous but could be slightly more specific about the type of text generation.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. With no sibling tools mentioned, there's no context about other available models or tools. It doesn't mention prerequisites, limitations, or ideal use cases. The agent receives only the basic function without usage context.

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. 1 tool updatev1.0.0
    • First observedqwen_max

TDQS

B3.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'qwen_max' has a clear and distinct purpose: generating text using the Qwen Max model.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'qwen_max' follows a single, consistent pattern with no deviations or mixing of conventions to evaluate.

Tool Count2/5

A single tool is too few for most server purposes, as it severely limits functionality and scope. While it might suffice for a minimal text generation service, it lacks the breadth typically expected for an MCP server, making it feel thin and under-scoped.

Completeness3/5

The tool provides a basic text generation capability, but there are notable gaps for a comprehensive AI model server. For example, it lacks tools for managing models, handling different input formats, or performing other common AI tasks like classification or summarization, which limits its utility.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers