Excel MCP Server

Instructions

Filter Excel data using a pandas query string.

Args:
    file_path: Path to the Excel file
    query: Pandas query string (e.g., "Age > 30 and Department == 'Sales'")
    sheet_name: Name of the sheet to filter (for Excel files)
    
Returns:
    Filtered data as string

Implementation Reference

• mcp_excel_server/server.py:368-411 (handler)

  The main handler function for the 'filter_excel' MCP tool. It reads data from an Excel-compatible file, applies a pandas query filter based on the provided query string, and returns the filtered DataFrame as a formatted string. The @mcp.tool() decorator registers it as an MCP tool.

  @mcp.tool()
  def filter_excel(file_path: str, query: str, sheet_name: Optional[str] = None) -> str:
      """
      Filter Excel data using a pandas query string.
      
      Args:
          file_path: Path to the Excel file
          query: Pandas query string (e.g., "Age > 30 and Department == 'Sales'")
          sheet_name: Name of the sheet to filter (for Excel files)
          
      Returns:
          Filtered data as string
      """
      try:
          # Read file
          _, ext = os.path.splitext(file_path)
          ext = ext.lower()
          
          read_params = {}
          if ext in ['.xlsx', '.xls', '.xlsm'] and sheet_name is not None:
              read_params["sheet_name"] = sheet_name
              
          if ext in ['.xlsx', '.xls', '.xlsm']:
              df = pd.read_excel(file_path, **read_params)
          elif ext == '.csv':
              df = pd.read_csv(file_path)
          elif ext == '.tsv':
              df = pd.read_csv(file_path, sep='\t')
          elif ext == '.json':
              df = pd.read_json(file_path)
          else:
              return f"Unsupported file extension: {ext}"
          
          # Apply filter
          filtered_df = df.query(query)
          
          # Return results
          if filtered_df.empty:
              return "No data matches the filter criteria."
          
          return filtered_df.to_string(index=False)
      except Exception as e:
          return f"Error filtering data: {str(e)}"