A Share MCP

Instructions

Implementation Reference

• src/tools/market_overview.py:30-46 (handler)

  MCP tool handler implementation for 'get_trade_dates'. This is the function executed when the tool is called, handling parameters, logging, and delegating to the use case via run_tool_with_handling.
  @app.tool() def get_trade_dates(start_date: Optional[str] = None, end_date: Optional[str] = None, limit: int = 250, format: str = "markdown") -> str: """ Fetch trading dates within a specified range. Args: start_date: Optional. Start date in 'YYYY-MM-DD' format. Defaults to 2015-01-01 if None. end_date: Optional. End date in 'YYYY-MM-DD' format. Defaults to the current date if None. Returns: Markdown table with 'is_trading_day' (1=trading, 0=non-trading). """ logger.info(f"Tool 'get_trade_dates' called for range {start_date or 'default'} to {end_date or 'default'}") return run_tool_with_handling( lambda: fetch_trade_dates(active_data_source, start_date=start_date, end_date=end_date, limit=limit, format=format), context="get_trade_dates", )
• mcp_server.py:54-54 (registration)

  Registration of market overview tools, including 'get_trade_dates', by calling register_market_overview_tools during app setup.
  register_market_overview_tools(app, active_data_source)
• src/data_source_interface.py:88-91 (schema)

  Interface definition specifying the signature for get_trade_dates method in FinancialDataSource.
  @abstractmethod def get_trade_dates(self, start_date: Optional[str] = None, end_date: Optional[str] = None) -> pd.DataFrame: """Fetches trading dates information within a range.""" pass
• src/use_cases/market_overview.py:9-13 (helper)

  Use case helper function that fetches trade dates from data source, applies validation and formatting.
  def fetch_trade_dates(data_source: FinancialDataSource, *, start_date: Optional[str], end_date: Optional[str], limit: int, format: str) -> str: validate_output_format(format) df = data_source.get_trade_dates(start_date=start_date, end_date=end_date) meta = {"start_date": start_date or "default", "end_date": end_date or "default"} return format_table_output(df, format=format, max_rows=limit, meta=meta)
• src/baostock_data_source.py:582-621 (helper)

  Concrete implementation in Baostock data source that queries the API for trade dates and returns a DataFrame.
  def get_trade_dates(self, start_date: Optional[str] = None, end_date: Optional[str] = None) -> pd.DataFrame: """Fetches trading dates using Baostock.""" logger.info( f"Fetching trade dates from {start_date or 'default'} to {end_date or 'default'}") try: with baostock_login_context(): # Login might not be strictly needed for this, but keeping consistent rs = bs.query_trade_dates( start_date=start_date, end_date=end_date) if rs.error_code != '0': logger.error( f"Baostock API error (Trade Dates): {rs.error_msg} (code: {rs.error_code})") # Unlikely to have 'no record found' for dates, but handle API errors raise DataSourceError( f"Baostock API error fetching trade dates: {rs.error_msg} (code: {rs.error_code})") data_list = [] while rs.next(): data_list.append(rs.get_row_data()) if not data_list: # This case should ideally not happen if the API returns a valid range logger.warning( f"No trade dates returned for range {start_date}-{end_date} (empty result set).") raise NoDataFoundError( f"No trade dates found for range {start_date}-{end_date} (empty result set).") result_df = pd.DataFrame(data_list, columns=rs.fields) logger.info(f"Retrieved {len(result_df)} trade date records.") return result_df except (LoginError, NoDataFoundError, DataSourceError, ValueError) as e: logger.warning( f"Caught known error fetching trade dates: {type(e).__name__}") raise e except Exception as e: logger.exception(f"Unexpected error fetching trade dates: {e}") raise DataSourceError( f"Unexpected error fetching trade dates: {e}")