A-Share MCP Server

Instructions

Implementation Reference

• src/tools/stock_market.py:111-138 (handler)

  The primary MCP tool handler for 'get_dividend_data'. Decorated with @app.tool(), it logs the call, invokes the fetch_dividend_data use case wrapped in error handling, and returns formatted results.
  @app.tool() def get_dividend_data(code: str, year: str, year_type: str = "report", limit: int = 250, format: str = "markdown") -> str: """ Fetches dividend information for a given stock code and year. Args: code: The stock code in Baostock format (e.g., 'sh.600000', 'sz.000001'). year: The year to query (e.g., '2023'). year_type: Type of year. Valid options (from Baostock): 'report': Announcement year (预案公告年份) 'operate': Ex-dividend year (除权除息年份) Defaults to 'report'. Returns: Dividend records table. """ logger.info(f"Tool 'get_dividend_data' called for {code}, year={year}, year_type={year_type}") return run_tool_with_handling( lambda: fetch_dividend_data( active_data_source, code=code, year=year, year_type=year_type, limit=limit, format=format, ), context=f"get_dividend_data:{code}:{year}", )
• mcp_server.py:51-51 (registration)

  The registration call in the main MCP server that registers all stock market tools, including 'get_dividend_data', via the register_stock_market_tools function.
  register_stock_market_tools(app, active_data_source)
• src/use_cases/stock_market.py:64-79 (helper)

  Helper use case function that performs input validation and formats the dividend DataFrame returned from the data source into the requested output format.
  def fetch_dividend_data( data_source: FinancialDataSource, *, code: str, year: str, year_type: str = "report", limit: int = 250, format: str = "markdown", ) -> str: validate_year(year) validate_year_type(year_type) validate_output_format(format) df = data_source.get_dividend_data(code=code, year=year, year_type=year_type) meta = {"code": code, "year": year, "year_type": year_type} return format_table_output(df, format=format, max_rows=limit, meta=meta)
• src/baostock_data_source.py:325-368 (helper)

  The core data fetching implementation in BaostockDataSource class, which queries the Baostock API (bs.query_dividend_data) to retrieve raw dividend data as a pandas DataFrame.
  def get_dividend_data(self, code: str, year: str, year_type: str = "report") -> pd.DataFrame: """Fetches dividend information using Baostock.""" logger.info( f"Fetching dividend data for {code}, year={year}, year_type={year_type}") try: with baostock_login_context(): rs = bs.query_dividend_data( code=code, year=year, yearType=year_type) if rs.error_code != '0': logger.error( f"Baostock API error (Dividend) for {code}: {rs.error_msg} (code: {rs.error_code})") if "no record found" in rs.error_msg.lower() or rs.error_code == '10002': raise NoDataFoundError( f"No dividend data found for {code} and year {year}. Baostock msg: {rs.error_msg}") else: raise DataSourceError( f"Baostock API error fetching dividend data: {rs.error_msg} (code: {rs.error_code})") data_list = [] while rs.next(): data_list.append(rs.get_row_data()) if not data_list: logger.warning( f"No dividend data found for {code}, year {year} (empty result set from Baostock).") raise NoDataFoundError( f"No dividend data found for {code}, year {year} (empty result set).") result_df = pd.DataFrame(data_list, columns=rs.fields) logger.info( f"Retrieved {len(result_df)} dividend records for {code}, year {year}.") return result_df except (LoginError, NoDataFoundError, DataSourceError, ValueError) as e: logger.warning( f"Caught known error fetching dividend data for {code}: {type(e).__name__}") raise e except Exception as e: logger.exception( f"Unexpected error fetching dividend data for {code}: {e}") raise DataSourceError( f"Unexpected error fetching dividend data for {code}: {e}")