Trading MCP Server

Instructions

Implementation Reference

• trader_tools.py:217-263 (handler)

  The 'simulate_sell' tool is registered using @mcp.tool() and implements logic to calculate the estimated profit/loss of a stock sale using FIFO matching, based on current holdings derived from a CSV and the live market price.

  @mcp.tool()
  def simulate_sell(symbol: str, shares: int) -> float:
      """Simulate selling a number of shares of a stock and estimate the profit or loss.
  
      Args:
          symbol: The stock ticker symbol to simulate the sale for (e.g., TSLA)
          shares: The number of shares to simulate selling.
  
      Returns:
          The estimated profit/loss from the simulated sale using FIFO matching, in dollars.
  
      Example:
          simulate_sell("AAPL", 50) -> 123.45
      """
      # Build current holdings for this symbol
      holdings = []
      for _, row in df.iterrows():
          if row['symbol'] != symbol:
              continue
          if row['type'] == 'Buy':
              holdings.append((row['shares'], row['price_per_share']))
          else:
              to_sell = row['shares']
              while to_sell > 0 and holdings:
                  qty, price = holdings[0]
                  matched = min(qty, to_sell)
                  if matched == qty:
                      holdings.pop(0)
                  else:
                      holdings[0] = (qty - matched, price)
                  to_sell -= matched
  
      proceeds = 0.0
      sell_price = get_live_price(symbol)
      to_sell = shares
  
      while to_sell > 0 and holdings:
          qty, buy_price = holdings[0]
          matched = min(qty, to_sell)
          proceeds += matched * (sell_price - buy_price)
          if matched == qty:
              holdings.pop(0)
          else:
              holdings[0] = (qty - matched, buy_price)
          to_sell -= matched
  
      return round(proceeds, 2)