China Stock MCP

Instructions

Implementation Reference

• src/china_stock_mcp/server.py:373-385 (handler)

  The main handler function decorated with @mcp.tool for registration. Fetches stock fund flow data using akshare based on symbol, determines market, formats output as DataFrame in specified format.

  @mcp.tool(name="get_fund_flow", description="获取股票资金流向数据 (近100交易日)")
  def get_fund_flow(
      symbol: Annotated[str, Field(description="股票代码 (例如: '000001')")],
      output_format: Annotated[
          Literal["json", "csv", "xml", "excel", "markdown", "html"],
          Field(description="输出数据格式: json, csv, xml, excel, markdown, html。默认: markdown"),
      ] = "markdown"
  ) -> str:   
      market = _get_market_from_symbol(symbol)
      df = ak.stock_individual_fund_flow(stock=symbol, market=market)
      if df.empty:
          df = pd.DataFrame()
      return _format_dataframe_output(df, output_format)

• src/china_stock_mcp/server.py:73-87 (helper)

  Helper function used by get_fund_flow to determine the stock market (sh/sz/bj) from the symbol prefix.

  def _get_market_from_symbol(symbol: str) -> str:
      """
      根据股票代码判断所属市场。
      上海证券交易所: sh (600, 601, 603, 605, 688 开头)
      深圳证券交易所: sz (000, 001, 002, 300 开头)
      北京证券交易所: bj (830, 870, 880 开头)
      默认返回 "sh"
      """
      if symbol.startswith(("600", "601", "603", "605", "688")):
          return "sh"
      elif symbol.startswith(("000", "001", "002", "300")):
          return "sz"
      elif symbol.startswith(("830", "870", "880")):
          return "bj"
      return "sh" # 默认上海市场

• src/china_stock_mcp/server.py:89-117 (helper)

  Helper function used by get_fund_flow to format the DataFrame output in various formats (json, csv, etc.).

  def _format_dataframe_output(
      df: pd.DataFrame,
      output_format: Literal["json", "csv", "xml", "excel", "markdown", "html"],
  ) -> str:
      """
      根据指定的格式格式化 DataFrame 输出。
      """
      if df.empty:
          return json.dumps([])
  
      if output_format == "json":
          return df.to_json(orient="records", force_ascii=False)
      elif output_format == "csv":
          return df.to_csv(index=False)
      elif output_format == "xml":
          return df.to_xml(index=False)
      elif output_format == "excel":
          # 使用 BytesIO 将 Excel 写入内存
          output = io.BytesIO()
          df.to_excel(output, index=False, engine='openpyxl')
          # 返回 base64 编码的二进制数据，或者直接返回字节流
          # 为了兼容性，这里尝试返回 utf-8 编码的字符串，但对于二进制文件，通常直接传输字节流更合适
          return output.getvalue().decode("utf-8", errors="ignore")
      elif output_format == "markdown":
          return df.to_markdown(index=False)
      elif output_format == "html":
          return df.to_html(index=False)
      else:
          return df.to_json(orient="records", force_ascii=False)