MonteWalk

Instructions

Implementation Reference

• tools/risk_engine.py:45-60 (handler)

  The main handler function for the 'var' tool, which computes the Value at Risk (VaR) for the current portfolio using historical returns and percentile method.

  def var(confidence: float = 0.95) -> str:
      """Calculates Value at Risk (VaR)."""
      data, weights = _get_portfolio_data()
      if data is None:
          return "Portfolio is empty."
      
      returns = data.pct_change().dropna()
      # Portfolio historical returns
      port_returns = returns.dot(weights)
      
      # Parametric VaR
      mean = np.mean(port_returns)
      std = np.std(port_returns)
      var_val = np.percentile(port_returns, (1 - confidence) * 100)
      
      return f"Daily VaR ({confidence:.0%}): {var_val:.2%}"

• server.py:380-383 (registration)

  Registration of the 'var' tool (imported from tools.risk_engine) as an MCP tool using the register_tools helper function, which applies @mcp.tool() decorator.

  register_tools(
      [portfolio_risk, var, max_drawdown, monte_carlo_simulation],
      "Risk Engine"
  )

• tools/risk_engine.py:10-30 (helper)

  Helper function _get_portfolio_data used by var (and other risk tools) to fetch portfolio positions, historical price data, and compute value weights.

  def _get_portfolio_data(lookback: str = "1y"):
      portfolio = get_positions()
      positions = portfolio.get("positions", {})
      if not positions:
          return None, None
      
      tickers = list(positions.keys())
      weights = np.array(list(positions.values())) # This is qty, need value weights
      
      # Fetch data
      data = yf.download(tickers, period=lookback, progress=False)['Close']
      if isinstance(data, pd.Series):
          data = data.to_frame(name=tickers[0])
          
      # Calculate current value weights
      current_prices = data.iloc[-1]
      values = current_prices * pd.Series(positions)
      total_value = values.sum()
      weights = values / total_value
      
      return data, weights