Qwen_Max MCP Server gives Claude access to Alibaba Cloud's Qwen model family via Dashscope - Qwen-Max, Qwen-Plus, and Qwen-Turbo - for text generation with customizable parameters, letting you call a second LLM provider directly from Claude Desktop.

Use it when you want to generate text using a Qwen model instead of or alongside Claude - for example, cross-checking output, using Qwen-Turbo's very large 1M-token context window for huge documents, or picking Qwen-Max for best-quality output within a 32K context. Tune temperature to the task: 0.0-0.3 for code generation, 0.3-0.5 for technical writing, 0.7 for general tasks, 0.8-1.0 for creative writing. Do not use it without a Dashscope API key - DASHSCOPE_API_KEY is required, though all models include a free quota of 1 million tokens to start.

• qwen_max: generate text using a Qwen model, with customizable parameters including max_tokens and temperature.

Three model variants are available: Qwen-Max (best performance, 32K context), Qwen-Plus (balanced performance/cost, 131K context), and Qwen-Turbo (fastest/lowest cost, 1M context).

Install automatically for Claude via Smithery:

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

Or from source:

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

Configure Claude Desktop:

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

Developers who want Claude to call Alibaba Cloud's Qwen models directly - for cross-provider comparison, cost-sensitive high-volume generation, or Qwen's very large context windows.