TA-Lib MCP Server

Instructions

Implementation Reference

• src/mcp_talib/core/server.py:336-349 (handler)

  The MCP tool handler for 'calculate_trima', registered with @mcp.tool(). Delegates computation to the 'trima' indicator from the registry.
  @mcp.tool() async def calculate_trima(close: List[float], timeperiod: int = 30) -> Dict[str, Any]: try: indicator = registry.get_indicator("trima") if not indicator: raise ValueError("TRIMA 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/trima.py:12-31 (helper)

  The TRIMAIndicator class containing the core implementation using TA-Lib's TRIMA function. Includes input schema definition and calculate method.
  class TRIMAIndicator(BaseIndicator): def __init__(self): super().__init__(name="trima", description="Triangular Moving Average (TRIMA)") @property 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"]} 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.TRIMA(close, timeperiod=timeperiod) return IndicatorResult(indicator_name=self.name, success=True, values={"trima": 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:42-42 (registration)

  Registration of the TRIMAIndicator class in the global indicator registry.
  registry.register("trima", TRIMAIndicator)
• src/mcp_talib/indicators/trima.py:16-19 (schema)

  Input schema definition for the TRIMA indicator, specifying close_prices array and timeperiod integer.
  @property 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"]}