MCP -Qwen_Max
MCP server for Qwen Max model
claude mcp add --transport stdio 66julienmartin-mcp-server-qwen_max node /path/to/Qwen_Max/build/index.js \ --env DASHSCOPE_API_KEY="your-api-key-here"
How to use
This MCP server implements the Qwen Max model integration for Claude Desktop via MCP. It exposes a server that runs the Qwen family models (Max, Plus, Turbo) under a Node.js/TypeScript stack and is designed to work with Claude Desktop through the MCP protocol. The example configuration shows how to wire the server into Claude Desktop by specifying the node command, the built server entry point, and the required environment variable for authentication with Dashscope. You can interact with the server using the MCP-compatible tool calls, such as sending a request with a model name and parameters like prompt, max_tokens, and temperature. The README also provides an API usage example demonstrating a tool call targeting the qwen_max model with typical generation parameters.
How to install
Prerequisites:
- Node.js v18 or higher
- npm
- Claude Desktop
- Dashscope API key
Installation steps:
- Quick install via Smithery (automatic deployment for Claude Desktop):
npx -y @smithery/cli install @66julienmartin/mcp-server-qwen_max --client claude
- Manual installation:
git clone https://github.com/66julienmartin/mcp-server-qwen-max.git
cd Qwen_Max
npm install
- Prepare configuration:
- Create a .env file in the project root with:
DASHSCOPE_API_KEY=your-api-key-here
- Run the development or production server as described in package.json scripts:
npm run dev # Watch mode
npm run build # Build
npm run start # Start server
Additional notes
Tips and considerations:
- The server relies on DASHSCOPE_API_KEY for access to Dashscope and should be kept secret.
- Update the model by editing src/index.ts (default model: qwen-max) and rebuilding if you modify the code.
- In Claude Desktop configuration, point the mcpServers entry to the built index.js and ensure the environment variable is provided.
- Supported models include qwen-max, qwen-plus, and qwen-turbo with corresponding versions; adjust the model name in the code or configuration as needed.
- Common issues to watch for: missing API keys, network errors, or model availability. Ensure Node.js version compatibility and correct paths to the built server entry point.
- You can adjust max_tokens, temperature, and other generation parameters via the MCP API usage example in the README and within your client requests.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.