Excel Finance MCP

Instructions

Implementation Reference

• src/tools/cash-flow-tools.ts:78-92 (handler)

  MCP tool handler for cash_burn_analysis that invokes the Python function via PythonBridge
  handler: async (args: any): Promise<ToolResult> => { try { const result = await pythonBridge.callPythonFunction({ module: 'cash_flow_tools', function: 'cash_burn_analysis', args: [args.monthsBack || 6] }); return result; } catch (error) { return { success: false, error: error instanceof Error ? error.message : String(error) }; } }
• src/tools/cash-flow-tools.ts:72-77 (schema)

  Input schema for the cash_burn_analysis tool, accepting optional monthsBack parameter (default 6)
  inputSchema: { type: "object", properties: { monthsBack: { type: "number", default: 6 } } },
• src/python/cash_flow_tools.py:29-34 (helper)

  Wrapper function in cash_flow_tools.py that instantiates CashFlowAnalyzer and calls its cash_burn_analysis method
  def cash_burn_analysis(months_back: int = 6) -> Dict[str, Any]: """Analyze cash burn rate and runway""" from cash_flow_analysis import CashFlowAnalyzer analyzer = CashFlowAnalyzer() return analyzer.cash_burn_analysis(months_back)
• src/python/cash_flow_analysis.py:282-340 (handler)

  Core implementation of cash_burn_analysis in CashFlowAnalyzer class, calculating burn rate, runway, trends, and recommendations
  def cash_burn_analysis(self, months_back: int = 6) -> Dict: """Analyze cash burn rate and runway""" end_date = date.today() start_date = end_date - timedelta(days=30 * months_back) monthly_flows = {} # Group flows by month for cf in self.cash_flows: if start_date <= cf.date <= end_date: month_key = cf.date.strftime('%Y-%m') if month_key not in monthly_flows: monthly_flows[month_key] = {'inflows': 0, 'outflows': 0} if cf.direction == CashFlowDirection.INFLOW: monthly_flows[month_key]['inflows'] += cf.amount else: monthly_flows[month_key]['outflows'] += cf.amount # Calculate burn rates monthly_burns = [] for month, flows in monthly_flows.items(): net_burn = flows['outflows'] - flows['inflows'] monthly_burns.append({ 'month': month, 'inflows': flows['inflows'], 'outflows': flows['outflows'], 'net_burn': net_burn }) if not monthly_burns: return {'error': 'No cash flow data found'} df = pd.DataFrame(monthly_burns) average_burn = df['net_burn'].mean() current_cash = self.opening_balance + sum( cf.amount * (1 if cf.direction == CashFlowDirection.INFLOW else -1) for cf in self.cash_flows ) # Calculate runway runway_months = current_cash / average_burn if average_burn > 0 else float('inf') # Trend analysis if len(monthly_burns) >= 3: recent_3_months = df.tail(3)['net_burn'].mean() trend = 'Improving' if recent_3_months < average_burn else 'Worsening' else: trend = 'Insufficient Data' return { 'current_cash_balance': round(current_cash, 2), 'average_monthly_burn': round(average_burn, 2), 'runway_months': round(runway_months, 1) if runway_months != float('inf') else 'Infinite', 'trend': trend, 'monthly_detail': monthly_burns, 'burn_rate_volatility': round(df['net_burn'].std(), 2), 'recommendation': self._get_burn_recommendation(runway_months, trend) }