llm_cloud_management
Manage cloud operations across AWS, Azure, and GCP using LLM-generated commands with research-driven best practices.
Instructions
LLM-managed cloud provider operations with research-driven approach
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| provider | Yes | Cloud provider to use | |
| action | Yes | Action to perform | |
| parameters | No | Action parameters | |
| llmInstructions | Yes | LLM instructions for command generation | |
| researchFirst | No | Research best approach first | |
| projectPath | No | Path to project directory | . |
| adrDirectory | No | Directory containing ADR files | docs/adrs |
Implementation Reference
- The core handler function that implements LLM-driven cloud management operations. Orchestrates research, LLM command generation, execution (simulated), and returns formatted results with analysis.export async function llmCloudManagement( args: { provider: 'aws' | 'azure' | 'gcp' | 'redhat' | 'ubuntu' | 'macos'; action: string; parameters?: Record<string, any>; llmInstructions: string; researchFirst?: boolean; projectPath?: string; adrDirectory?: string; }, context?: ToolContext ): Promise<any> { const { provider, action, parameters = {}, llmInstructions, researchFirst = true, projectPath, adrDirectory, } = args; if (!provider || !action || !llmInstructions) { throw new McpAdrError( 'Provider, action, and llmInstructions are required', 'MISSING_REQUIRED_PARAMS' ); } try { context?.info(`🔧 Initializing ${provider} cloud management for: ${action}`); context?.report_progress(0, 100); // Initialize research orchestrator const orchestrator = new ResearchOrchestrator(projectPath, adrDirectory); let researchResult = null; if (researchFirst) { context?.info('📚 Researching best practices and documentation...'); context?.report_progress(20, 100); // Step 1: Research the best approach const researchQuery = ` How to ${action} on ${provider} platform? Best practices for ${provider} ${action} ${provider} ${action} documentation and examples Security considerations for ${provider} ${action} ${llmInstructions} `; researchResult = await orchestrator.answerResearchQuestion(researchQuery); } // Step 2: Generate command using LLM context?.info('🤖 Generating commands with LLM guidance...'); context?.report_progress(50, 100); const command = await generateCloudCommand({ provider, action, parameters, research: researchResult, instructions: llmInstructions, }); // Step 3: Execute the command (simulated for now) context?.info(`☁️ Executing ${provider} operation...`); context?.report_progress(80, 100); const executionResult = await executeCloudCommand(command); context?.info('✅ Cloud operation complete!'); context?.report_progress(100, 100); return { content: [ { type: 'text', text: `# LLM-Managed Cloud Operation ## Operation Details - **Provider**: ${provider} - **Action**: ${action} - **Parameters**: ${JSON.stringify(parameters, null, 2)} ## LLM Instructions ${llmInstructions} ${ researchResult ? ` ## Research Results - **Confidence**: ${(researchResult.confidence * 100).toFixed(1)}% - **Sources**: ${researchResult.metadata.sourcesQueried.join(', ')} - **Research Summary**: ${researchResult.answer} ` : '' } ## Generated Command \`\`\`bash ${command.generated} \`\`\` ## Execution Result ${executionResult.success ? '✅ Success' : '❌ Failed'} ${executionResult.output ? `\n\`\`\`\n${executionResult.output}\n\`\`\`` : ''} ## LLM Analysis ${command.analysis || 'No analysis available'} ## Metadata - **Command Confidence**: ${(command.confidence * 100).toFixed(1)}% - **Timestamp**: ${new Date().toISOString()} - **Research-Driven**: ${researchFirst ? 'Yes' : 'No'} `, }, ], }; } catch (error) { throw new McpAdrError( `Cloud management operation failed: ${error instanceof Error ? error.message : String(error)}`, 'CLOUD_MANAGEMENT_ERROR' ); } }
- src/tools/tool-catalog.ts:702-721 (schema)Tool catalog registration providing metadata, input schema, and categorization for the llm_cloud_management tool.TOOL_CATALOG.set('llm_cloud_management', { name: 'llm_cloud_management', shortDescription: 'Cloud management via LLM', fullDescription: 'Cloud resource management with LLM assistance.', category: 'research', complexity: 'complex', tokenCost: { min: 3000, max: 6000 }, hasCEMCPDirective: true, // Phase 4.3: Complex tool - cloud management orchestration relatedTools: ['llm_web_search', 'llm_database_management'], keywords: ['cloud', 'management', 'llm', 'aws', 'gcp', 'azure'], requiresAI: true, inputSchema: { type: 'object', properties: { operation: { type: 'string' }, provider: { type: 'string', enum: ['aws', 'gcp', 'azure'] }, }, required: ['operation'], }, });
- Helper function for generating cloud commands using LLM (currently placeholder implementation).async function generateCloudCommand(context: { provider: string; action: string; parameters: Record<string, any>; research: any; instructions: string; }): Promise<{ generated: string; confidence: number; analysis: string }> { // const { loadAIConfig, getAIExecutor } = await import('../config/ai-config.js'); // const aiConfig = loadAIConfig(); // const executor = getAIExecutor(); // const prompt = ` // Generate a ${context.provider} command for the following operation: // // Action: ${context.action} // Parameters: ${JSON.stringify(context.parameters, null, 2)} // Instructions: ${context.instructions} // // ${context.research ? ` // Research Context: // - Confidence: ${(context.research.confidence * 100).toFixed(1)}% // - Sources: ${context.research.metadata.sourcesQueried.join(', ')} // - Key Findings: ${context.research.answer} // ` : ''} // // Provider Context: // ${getProviderContext(context.provider)} // // Generate the CLI command and provide analysis of the approach. // `; // TODO: Implement LLM command generation when AI executor is available // const result = await executor.executeStructuredPrompt(prompt, { // type: 'object', // properties: { // command: { type: 'string' }, // confidence: { type: 'number' }, // analysis: { type: 'string' } // } // }); // return { // generated: result.data.command || 'echo "Command generation failed"', // confidence: result.data.confidence || 0.5, // analysis: result.data.analysis || 'No analysis available' // }; // Placeholder implementation return { generated: `echo "LLM command generation for ${context.provider} ${context.action} not yet implemented"`, confidence: 0.3, analysis: 'LLM command generation is not yet available. This is a placeholder implementation.', }; }
- Helper function for executing generated cloud commands (simulated).async function executeCloudCommand(command: { generated: string; confidence: number; }): Promise<{ success: boolean; output: string }> { // For now, simulate command execution // In a real implementation, this would execute the actual command return { success: command.confidence > 0.7, output: `Simulated execution of: ${command.generated}\n\nThis is a simulation. In production, this would execute the actual command.`, }; }
- Tool listing in server context generator with name and description.{ name: 'llm_cloud_management', description: 'Manage cloud resources and infrastructure' }, { name: 'llm_database_management', description: 'Manage database operations and queries' },