qwen3_code_generate
Generate code from natural language descriptions in specified programming languages using the Qwen3-Coder model.
Instructions
Generate code using Qwen3-Coder
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Description of what code to generate | |
| language | No | Target programming language |
Implementation Reference
- qwen3-mcp-server.js:98-115 (registration)Registration of the 'qwen3_code_generate' tool, including name, description, and input schema definition.
{ name: "qwen3_code_generate", description: "Generate code using Qwen3-Coder", inputSchema: { type: "object", properties: { prompt: { type: "string", description: "Description of what code to generate" }, language: { type: "string", description: "Target programming language" } }, required: ["prompt"] } }, - qwen3-mcp-server.js:195-204 (handler)Handler for 'qwen3_code_generate': constructs a specific prompt based on input arguments and calls the shared Qwen3-Coder function.
case "qwen3_code_generate": prompt = `Generate ${args.language || 'code'} for the following requirement: ${args.prompt} ${args.language ? `Please write the code in ${args.language}.` : ''} Provide clean, well-documented code with explanations.`; result = await callQwen3Coder(prompt); break; - qwen3-mcp-server.js:25-56 (helper)Shared helper function that spawns Ollama process to run Qwen3-Coder model with the given prompt and returns the output.
async function callQwen3Coder(prompt, options = {}) { return new Promise((resolve, reject) => { const ollamaProcess = spawn('ollama', ['run', 'qwen3-coder:30b', prompt], { stdio: ['pipe', 'pipe', 'pipe'] }); let output = ''; let error = ''; ollamaProcess.stdout.on('data', (data) => { output += data.toString(); }); ollamaProcess.stderr.on('data', (data) => { error += data.toString(); }); ollamaProcess.on('close', (code) => { if (code === 0) { resolve(output.trim()); } else { reject(new Error(`Ollama process exited with code ${code}: ${error}`)); } }); // Set timeout for long-running requests setTimeout(() => { ollamaProcess.kill(); reject(new Error('Request timeout')); }, options.timeout || 120000); // 2 minutes default timeout }); }