Qwen Max MCP Server

Qwen Max MCP Server provides seamless integration with Alibaba Cloud's powerful Qwen language models directly through Claude Desktop. This implementation supports all commercial Qwen models including Max, Plus, and Turbo variants, giving you access to models with extensive context windows up to 1 million tokens. The server handles all communication with the Dashscope API, providing proper error handling, configurable parameters, and streaming responses. Built with Node.js/TypeScript for optimal stability and reliability with MCP servers, it offers a straightforward way to leverage Qwen's capabilities for complex reasoning, code generation, and creative tasks.

Overview

Qwen Max MCP Server allows you to access Alibaba Cloud's Qwen language models directly through Claude Desktop. This implementation supports all commercial Qwen models with their extensive context windows and specialized capabilities.

Prerequisites

Before installing the Qwen Max MCP Server, ensure you have:

Node.js (v18 or higher)
npm
Claude Desktop
Dashscope API key from Alibaba Cloud

Installation Options

Automatic Installation via Smithery

The easiest way to install Qwen Max MCP Server is through Smithery:

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

Manual Installation

If you prefer to install manually:

Clone the repository:

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

Build the project:

npm run build

Configuration

Create a .env file in the project root with your API key:

DASHSCOPE_API_KEY=your-api-key-here

Update your Claude Desktop configuration to include the MCP server.

Model Selection

By default, this server uses the Qwen-Max model, but you can choose from several options:

Qwen-Max

Best for complex and multi-step tasks
Context window: 32,768 tokens
Max input: 30,720 tokens, Max output: 8,192 tokens
Pricing: $0.0016/1K tokens (input), $0.0064/1K tokens (output)

Qwen-Plus

Balanced performance, speed, and cost
Context window: 131,072 tokens
Max input: 129,024 tokens, Max output: 8,192 tokens
Pricing: $0.0004/1K tokens (input), $0.0012/1K tokens (output)

Qwen-Turbo

Fast speed and low cost for simple tasks
Context window: 1,000,000 tokens
Max input: 1,000,000 tokens, Max output: 8,192 tokens
Pricing: $0.00005/1K tokens (input), $0.0002/1K tokens (output)

To modify the model, update the model name in src/index.ts:

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

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

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

Temperature Settings

The temperature parameter controls the randomness of the model's output:

Lower values (0.0-0.7): More focused and deterministic outputs
Higher values (0.7-1.0): More creative and varied outputs

Recommended temperature settings by task:

Code generation: 0.0-0.3
Technical writing: 0.3-0.5
General tasks: 0.7 (default)
Creative writing: 0.8-1.0

Error Handling

The server provides detailed error messages for common issues:

API authentication errors
Invalid parameters
Rate limiting
Network issues
Token limit exceeded
Model availability issues

Development

For development work on the server:

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