MCP GitHub Project Manager

Instructions

Input Schema

Input Schema (JSON Schema)

Implementation Reference

• src/infrastructure/tools/ai-tasks/GetNextTaskTool.ts:27-127 (handler)

  Main handler function that executes the get_next_task tool logic: processes arguments, generates mock tasks, applies filters, sorts by priority/complexity, generates AI analysis, and returns formatted recommendations.
  async function executeGetNextTask(args: GetNextTaskArgs): Promise<MCPResponse> { const taskService = new TaskGenerationService(); try { // For now, create mock tasks for demonstration // In a full implementation, this would integrate with ResourceManager const mockTasks = [ { id: 'task-1', title: 'Set up project infrastructure', description: 'Initialize project structure, CI/CD, and development environment', priority: 'high', complexity: 4, estimatedHours: 8, status: 'pending', dependencies: [], tags: ['setup', 'infrastructure'] }, { id: 'task-2', title: 'Implement user authentication', description: 'Create login, registration, and password reset functionality', priority: 'critical', complexity: 6, estimatedHours: 16, status: 'pending', dependencies: ['task-1'], tags: ['auth', 'security'] }, { id: 'task-3', title: 'Design database schema', description: 'Create database tables and relationships for core entities', priority: 'high', complexity: 5, estimatedHours: 12, status: 'pending', dependencies: ['task-1'], tags: ['database', 'design'] } ]; // Apply filters let filteredTasks = mockTasks; if (args.maxComplexity) { filteredTasks = filteredTasks.filter(task => task.complexity <= args.maxComplexity!); } if (args.assignee) { // Would filter by assignee in real implementation } // Get recommendations (simplified) const recommendations = filteredTasks .sort((a, b) => { // Sort by priority first, then complexity const priorityOrder = { critical: 4, high: 3, medium: 2, low: 1 }; const priorityDiff = (priorityOrder[b.priority as keyof typeof priorityOrder] || 0) - (priorityOrder[a.priority as keyof typeof priorityOrder] || 0); if (priorityDiff !== 0) return priorityDiff; return a.complexity - b.complexity; // Prefer lower complexity }) .slice(0, args.limit); // Calculate sprint fit const totalHours = recommendations.reduce((sum, task) => sum + task.estimatedHours, 0); const sprintCapacity = args.sprintCapacity || 40; const sprintFit = totalHours <= sprintCapacity; // Generate AI analysis const analysis = args.includeAnalysis ? generateTaskAnalysis(recommendations, args) : null; // Format response const summary = formatNextTaskRecommendations(recommendations, analysis, { totalHours, sprintCapacity, sprintFit, filtersApplied: getAppliedFilters(args) }); return ToolResultFormatter.formatSuccess('get_next_task', { summary, recommendations, analysis, metrics: { totalTasks: recommendations.length, totalHours, sprintCapacity, sprintFit } }); } catch (error) { process.stderr.write(`Error in get_next_task tool: ${error}\n`); return ToolResultFormatter.formatSuccess('get_next_task', { error: `Failed to get task recommendations: ${error instanceof Error ? error.message : 'Unknown error'}`, success: false }); } }
• src/infrastructure/tools/ai-tasks/GetNextTaskTool.ts:8-20 (schema)

  Zod schema defining the input parameters for the get_next_task tool, including optional filters like projectId, assignee, sprintCapacity, etc.
  const getNextTaskSchema = z.object({ projectId: z.string().optional().describe('Filter tasks by specific project ID'), featureId: z.string().optional().describe('Filter tasks by specific feature ID'), assignee: z.string().optional().describe('Filter tasks for specific team member'), teamSkills: z.array(z.string()).optional().describe('Team skills to match against task requirements'), sprintCapacity: z.number().optional().describe('Available hours in current sprint (default: 40)'), currentPhase: z.enum(['planning', 'development', 'testing', 'review', 'deployment']).optional() .describe('Focus on tasks in specific phase'), excludeBlocked: z.boolean().default(true).describe('Whether to exclude blocked tasks'), maxComplexity: z.number().min(1).max(10).optional().describe('Maximum task complexity to consider'), includeAnalysis: z.boolean().default(true).describe('Whether to include detailed AI analysis'), limit: z.number().min(1).max(20).default(5).describe('Maximum number of tasks to recommend') });
• src/infrastructure/tools/ToolRegistry.ts:192-199 (registration)

  Registration of the getNextTaskTool in the central ToolRegistry singleton during initialization of built-in AI task management tools.
  this.registerTool(addFeatureTool); this.registerTool(generatePRDTool); this.registerTool(parsePRDTool); this.registerTool(getNextTaskTool); this.registerTool(analyzeTaskComplexityTool); this.registerTool(expandTaskTool); this.registerTool(enhancePRDTool); this.registerTool(createTraceabilityMatrixTool);
• src/index.ts:368-369 (registration)

  Dispatch case in the MCP server request handler that routes 'call_tool' requests for get_next_task to the executeGetNextTask function.
  case "get_next_task": return await executeGetNextTask(args);
• src/infrastructure/tools/ai-tasks/GetNextTaskTool.ts:287-305 (schema)

  ToolDefinition object for get_next_task including name, description, schema reference, and usage examples.
  export const getNextTaskTool: ToolDefinition<GetNextTaskArgs> = { name: "get_next_task", description: "Get AI-powered recommendations for the next task to work on based on priorities, dependencies, team capacity, and current project state", schema: getNextTaskSchema as unknown as ToolSchema<GetNextTaskArgs>, examples: [ { name: "Get next task for development", description: "Get the next recommended task for a developer with specific skills", args: { teamSkills: ["typescript", "react", "node.js"], sprintCapacity: 40, maxComplexity: 7, excludeBlocked: true, includeAnalysis: true, limit: 3 } } ] };