TA-Lib MCP Server

Instructions

Implementation Reference

• src/mcp_talib/core/server.py:265-278 (handler)

  The MCP tool handler for 'calculate_midprice', decorated with @mcp.tool() for automatic registration. Delegates computation to the 'midprice' indicator from the registry.

  @mcp.tool()
  async def calculate_midprice(high: List[float], low: List[float], timeperiod: int = 14) -> Dict[str, Any]:
      try:
          indicator = registry.get_indicator("midprice")
          if not indicator:
              raise ValueError("MIDPRICE indicator not found")
          market_data = MarketData(close=[0], high=high, low=low)
          result = await indicator.calculate(market_data, {"timeperiod": timeperiod})
          if result.success:
              return {"success": True, "values": result.values, "metadata": result.metadata}
          return {"success": False, "error": result.error_message}
      except Exception as e:
          return {"success": False, "error": str(e)}

• src/mcp_talib/indicators/midprice.py:12-41 (helper)

  Core implementation of midprice calculation using TA-Lib's MIDPRICE function. Includes input schema and the calculate method that performs (high + low)/2 averaged over timeperiod.

  class MIDPRICEIndicator(BaseIndicator):
      def __init__(self):
          super().__init__(name="midprice", description="Midpoint Price over period")
  
      @property
      def input_schema(self) -> Dict[str, Any]:
          return {
              "type": "object",
              "properties": {
                  "high_prices": {"type": "array", "items": {"type": "number"}},
                  "low_prices": {"type": "array", "items": {"type": "number"}},
                  "timeperiod": {"type": "integer", "default": 14},
              },
              "required": ["high_prices", "low_prices"],
          }
  
      async def calculate(self, market_data: MarketData, options: Dict[str, Any] = None) -> IndicatorResult:
          if options is None:
              options = {}
          timeperiod = options.get("timeperiod", 14)
  
          high = np.asarray(market_data.high or [], dtype=float)
          low = np.asarray(market_data.low or [], dtype=float)
  
          try:
              out = ta.MIDPRICE(high, low, timeperiod=timeperiod)
              return IndicatorResult(indicator_name=self.name, success=True, values={"midprice": out.tolist()}, metadata={"timeperiod": timeperiod, "input_points": len(high), "output_points": len(out)})
          except Exception as e:
              return IndicatorResult(indicator_name=self.name, success=False, values={}, error_message=str(e))

• src/mcp_talib/indicators/__init__.py:37-37 (registration)

  Registration of the MIDPRICEIndicator class in the central indicator registry, allowing it to be retrieved by name in tool handlers.

  registry.register("midprice", MIDPRICEIndicator)

• src/mcp_talib/indicators/midprice.py:17-26 (schema)

  JSON schema defining the input parameters for the midprice indicator, matching the tool's high_prices, low_prices, and timeperiod.

  def input_schema(self) -> Dict[str, Any]:
      return {
          "type": "object",
          "properties": {
              "high_prices": {"type": "array", "items": {"type": "number"}},
              "low_prices": {"type": "array", "items": {"type": "number"}},
              "timeperiod": {"type": "integer", "default": 14},
          },
          "required": ["high_prices", "low_prices"],
      }