TA-Lib MCP Server

Instructions

Implementation Reference

• src/mcp_talib/core/server.py:222-234 (handler)

  MCP tool handler function for 'calculate_mama' that fetches the MAMA indicator from registry and computes using input close prices, fastlimit, and slowlimit.
  @mcp.tool() async def calculate_mama(close: List[float], fastlimit: float = 0.5, slowlimit: float = 0.05) -> Dict[str, Any]: try: indicator = registry.get_indicator("mama") if not indicator: raise ValueError("MAMA indicator not found") market_data = MarketData(close=close) result = await indicator.calculate(market_data, {"fastlimit": fastlimit, "slowlimit": slowlimit}) 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/mama.py:28-44 (helper)

  Core implementation of MAMA calculation using TA-Lib's ta.MAMA function, returns MAMA and FAMA values.
  async def calculate(self, market_data: MarketData, options: Dict[str, Any] = None) -> IndicatorResult: if options is None: options = {} fastlimit = options.get("fastlimit", 0.5) slowlimit = options.get("slowlimit", 0.05) close = np.asarray(market_data.close, dtype=float) try: mama, fama = ta.MAMA(close, fastlimit=fastlimit, slowlimit=slowlimit) return IndicatorResult( indicator_name=self.name, success=True, values={"mama": mama.tolist(), "fama": fama.tolist()}, metadata={"fastlimit": fastlimit, "slowlimit": slowlimit, "input_points": len(close), "output_points": len(mama)}, ) except Exception as e: return IndicatorResult(indicator_name=self.name, success=False, values={}, error_message=str(e))
• src/mcp_talib/indicators/__init__.py:34-34 (registration)

  Registers the MAMAIndicator class in the indicator registry under the 'mama' key, used by tool handlers.
  registry.register("mama", MAMAIndicator)
• src/mcp_talib/indicators/mama.py:17-26 (schema)

  JSON schema defining input parameters for the MAMA indicator (close_prices required, fastlimit/slowlimit optional).
  def input_schema(self) -> Dict[str, Any]: return { "type": "object", "properties": { "close_prices": {"type": "array", "items": {"type": "number"}}, "fastlimit": {"type": "number", "default": 0.5}, "slowlimit": {"type": "number", "default": 0.05}, }, "required": ["close_prices"], }
• src/mcp_talib/core/mcp_server.py:76-81 (schema)

  Tool specification schema in TOOL_SPECS for dynamic tool creation, defining params and defaults for calculate_mama.
  "mama": { "description": "MESA Adaptive Moving Average (MAMA)", "params": {"close": List[float], "fastlimit": float, "slowlimit": float}, "defaults": {"fastlimit": 0.5, "slowlimit": 0.05}, "market_data_args": {"close": "close"}, },