qwen_maxLABSCO SUMMARY
The interesting use is a second opinion, not a replacement.
Reaching a different model family from inside your main assistant is most useful when the two disagree — Qwen's training and refusal behaviour differ enough from Western models that the disagreement is informative, particularly on Chinese-language material. The author's note about choosing Node for SDK stability is a small honest detail: they picked the runtime with better tooling rather than the one they preferred.
What it is
A thin server that gives an assistant access to Qwen Max, Alibaba's large model, via the Dashscope API.
What you get
Qwen Max as a callable model from whatever client you already use.
Requirements
Node, npm, and a Dashscope API key. MIT licensed.
Setup effort
Build from source — git clone https://github.com/kamelirzouni/MCP-server-Qwen_Max
USE CASES
01
Getting a second opinion
A different model family, called from the same conversation.
02
Working in Chinese
A model trained heavily on it.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- Node.js
- DASHSCOPE_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/kamelirzouni/MCP-server-Qwen_Max
cd MCP-server-Qwen_Max
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"qwen_max": {
"command": "node",
"args": [
"<YOUR_PATH_TO_QWEN_MAX>/build/index.js"
],
"env": {
"DASHSCOPE_API_KEY": "<YOUR_DASHSCOPE_API_KEY>"
}
}
}
}
