select_columns

Instructions

Implementation Reference

• src/csv_editor/tools/transformations.py:164-206 (handler)

  The actual handler for the select_columns tool. Gets the session, validates columns exist in the dataframe, selects only the specified columns using df[columns].copy(), records the operation, and returns success/error.

  async def select_columns(
      session_id: str, columns: list[str], ctx: Context = None
  ) -> dict[str, Any]:
      """
      Select specific columns from the dataframe.
  
      Args:
          session_id: Session identifier
          columns: List of column names to keep
          ctx: FastMCP context
  
      Returns:
          Dict with success status and selected columns
      """
      try:
          manager = get_session_manager()
          session = manager.get_session(session_id)
  
          if not session or session.df is None:
              return {"success": False, "error": "Invalid session or no data loaded"}
  
          df = session.df
  
          # Validate columns exist
          missing_cols = [col for col in columns if col not in df.columns]
          if missing_cols:
              return {"success": False, "error": f"Columns not found: {missing_cols}"}
  
          session.df = df[columns].copy()
          session.record_operation(
              OperationType.SELECT,
              {"columns": columns, "columns_before": df.columns.tolist(), "columns_after": columns},
          )
  
          return {
              "success": True,
              "selected_columns": columns,
              "columns_removed": [col for col in df.columns if col not in columns],
          }
  
      except Exception as e:
          logger.error(f"Error selecting columns: {e!s}")
          return {"success": False, "error": str(e)}

• src/csv_editor/server.py:211-216 (registration)

  The MCP tool registration/decorator for select_columns. Uses @mcp.tool decorator to register the function, defines the FastMCP API with session_id and columns parameters, and delegates to the actual implementation via _select_columns.

  @mcp.tool
  async def select_columns(
      session_id: str, columns: list[str], ctx: Context = None
  ) -> dict[str, Any]:
      """Select specific columns from the dataframe."""
      return await _select_columns(session_id, columns, ctx)

• src/csv_editor/server.py:69-80 (schema)

  The tool is listed under capabilities in the server info, documenting select_columns as a data_manipulation capability.

  "data_manipulation": [
      "filter_rows",
      "sort_data",
      "select_columns",
      "rename_columns",
      "add_column",
      "remove_columns",
      "change_column_type",
      "fill_missing_values",
      "remove_duplicates",
  ],
  "data_analysis": [