TA-Lib MCP Server

Instructions

Implementation Reference

• src/mcp_talib/core/server.py:350-362 (handler)

  The MCP tool handler for 'calculate_wma', decorated with @mcp.tool(). It retrieves the 'wma' indicator from the registry, prepares market data, calls the indicator's calculate method, and returns the result.
  @mcp.tool() async def calculate_wma(close: List[float], timeperiod: int = 30) -> Dict[str, Any]: try: indicator = registry.get_indicator("wma") if not indicator: raise ValueError("WMA indicator not found") market_data = MarketData(close=close) 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/wma.py:20-30 (helper)

  Core implementation of the WMA calculation using TA-Lib's WMA function. This is the supporting utility called by the tool handler.
  async def calculate(self, market_data: MarketData, options: Dict[str, Any] = None) -> IndicatorResult: if options is None: options = {} timeperiod = options.get("timeperiod", 30) close = np.asarray(market_data.close, dtype=float) try: out = ta.WMA(close, timeperiod=timeperiod) return IndicatorResult(indicator_name=self.name, success=True, values={"wma": out.tolist()}, metadata={"timeperiod": timeperiod, "input_points": len(close), "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:43-43 (registration)

  Registers the WMAIndicator class in the global indicator registry, allowing the tool handler to retrieve it via registry.get_indicator('wma').
  registry.register("wma", WMAIndicator)
• src/mcp_talib/indicators/wma.py:17-18 (schema)

  Input schema definition for the WMA indicator, specifying expected parameters like close_prices and timeperiod.
  def input_schema(self) -> Dict[str, Any]: return {"type": "object", "properties": {"close_prices": {"type": "array", "items": {"type": "number"}}, "timeperiod": {"type": "integer", "default": 30}}, "required": ["close_prices"]}