VisiData MCP Server

Instructions

Implementation Reference

• src/visidata_mcp/server.py:491-552 (handler)

  The sort_data tool implementation registered with @mcp.tool() decorator. This function loads data using pandas, sorts it by a specified column in ascending or descending order, optionally saves the sorted data to an output file, and returns sorting information as JSON.

  @mcp.tool()
  def sort_data(file_path: str, column: str, descending: bool = False, output_path: Optional[str] = None) -> str:
      """
      Sort data by a specific column.
      
      Args:
          file_path: Path to the data file
          column: Column name to sort by
          descending: Sort in descending order (default: False)
          output_path: Optional path to save sorted data
      
      Returns:
          Information about the sorted data
      """
      try:
          import pandas as pd
          from pathlib import Path
          
          file_extension = Path(file_path).suffix.lower()
          
          # Load with pandas
          if file_extension == '.csv':
              df = pd.read_csv(file_path)
          elif file_extension == '.json':
              df = pd.read_json(file_path)
          elif file_extension in ['.xlsx', '.xls']:
              df = pd.read_excel(file_path)
          elif file_extension == '.tsv':
              df = pd.read_csv(file_path, sep='\t')
          else:
              df = pd.read_csv(file_path)
          
          if column not in df.columns:
              return f"Error: Column '{column}' not found. Available columns: {list(df.columns)}"
          
          # Sort the data
          sorted_df = df.sort_values(by=column, ascending=not descending)
          
          result = {
              "sorted_by": column,
              "descending": descending,
              "total_rows": len(sorted_df)
          }
          
          # If output path is specified, save sorted data
          if output_path:
              output_extension = Path(output_path).suffix.lower()
              if output_extension == '.csv':
                  sorted_df.to_csv(output_path, index=False)
              elif output_extension == '.json':
                  sorted_df.to_json(output_path, orient='records', indent=2)
              elif output_extension in ['.xlsx', '.xls']:
                  sorted_df.to_excel(output_path, index=False)
              else:
                  # Default to CSV
                  sorted_df.to_csv(output_path, index=False)
              result["saved_to"] = output_path
          
          return json.dumps(result, indent=2)
          
      except Exception as e:
          return f"Error sorting data: {str(e)}\n{traceback.format_exc()}"