load-csv

Instructions

Implementation Reference

• claude_mcp_data_explorer/tools/data_loader.py:13-54 (handler)

  Primary handler for 'load-csv' tool in Python implementation. Loads CSV using pandas, supports chunking for large files, stores DataFrame globally, and provides summary statistics.

  async def handle_load_csv(arguments):
      """Handle the load-csv tool"""
      global _df_counter
      
      csv_path = arguments.get("csv_path")
      df_name = arguments.get("df_name")
      
      if not csv_path:
          return [TextContent(type="text", text="Error: csv_path is required")]
      
      # Normalize path for Windows
      csv_path = os.path.normpath(csv_path)
      
      # Generate a default name if none provided
      if not df_name:
          df_name = f"df_{_df_counter}"
          _df_counter += 1
      
      try:
          # Get file size
          file_size_mb = os.path.getsize(csv_path) / (1024 * 1024)
          logging.info(f"Loading CSV file: {csv_path} ({file_size_mb:.2f} MB)")
          
          # Use chunking for large files
          if file_size_mb > 100:
              return await _load_large_csv(csv_path, df_name)
          else:
              return await _load_small_csv(csv_path, df_name)
      
      except FileNotFoundError:
          return [TextContent(
              type="text", 
              text=f"Error: File not found: {csv_path}"
          )]
      except Exception as e:
          error_message = f"Error loading CSV: {str(e)}\n{traceback.format_exc()}"
          logging.error(error_message)
          return [TextContent(
              type="text", 
              text=f"Error loading CSV: {str(e)}"
          )]

• src/tools/data-loader.ts:19-72 (handler)

  Primary handler for 'load-csv' tool in TypeScript implementation. Parses CSV using PapaParse, stores data globally, generates summary using simple-statistics library.

  export async function loadCsv(args: LoadCsvArgs): Promise<{ type: string, text: string }[]> {
    const { csv_path, df_name } = args;
    
    if (!csv_path) {
      return [{ type: 'text', text: 'Error: csv_path is required' }];
    }
    
    // Normalize path for Windows
    const normalizedPath = path.normalize(csv_path);
    
    // Generate a default name if none provided
    const dataFrameName = df_name || `df_${dfCounter++}`;
    
    try {
      // Check if file exists
      if (!fs.existsSync(normalizedPath)) {
        return [{ type: 'text', text: `Error: File not found: ${normalizedPath}` }];
      }
      
      // Get file size
      const stats = fs.statSync(normalizedPath);
      const fileSizeMb = stats.size / (1024 * 1024);
      
      // Read file content
      const fileContent = fs.readFileSync(normalizedPath, 'utf8');
      
      // Parse CSV
      const parseResult = Papa.parse(fileContent, {
        header: true,
        dynamicTyping: true,
        skipEmptyLines: true
      });
      
      if (parseResult.errors && parseResult.errors.length > 0) {
        return [{ type: 'text', text: `Error parsing CSV: ${parseResult.errors[0].message}` }];
      }
      
      const data = parseResult.data as any[];
      
      // Store in global storage
      dataFrames[dataFrameName] = data;
      
      // Generate summary
      const summary = generateSummary(data, parseResult.meta.fields || []);
      
      return [{ 
        type: 'text', 
        text: `Successfully loaded ${normalizedPath} as ${dataFrameName} (${data.length} rows × ${parseResult.meta.fields?.length || 0} columns)\n\n${summary}` 
      }];
      
    } catch (error: any) {
      return [{ type: 'text', text: `Error loading CSV: ${error.message}` }];
    }
  }

• claude_mcp_data_explorer/server.py:39-56 (registration)

  Registration of the 'load-csv' tool including schema in the Python MCP server's list_tools handler.

  types.Tool(
      name="load-csv",
      description="Load a CSV file into a DataFrame for analysis",
      inputSchema={
          "type": "object",
          "properties": {
              "csv_path": {
                  "type": "string",
                  "description": "Path to the CSV file to load"
              },
              "df_name": {
                  "type": "string",
                  "description": "Name for the DataFrame (optional, defaults to df_1, df_2, etc.)"
              }
          },
          "required": ["csv_path"]
      }
  ),

• src/index.ts:56-71 (registration)

  Registration of the 'load-csv' tool including schema in the TypeScript MCP server's listTools handler.

  name: "load-csv",
  description: "Load a CSV file into a DataFrame for analysis",
  inputSchema: {
    type: "object",
    properties: {
      csv_path: {
        type: "string",
        description: "Path to the CSV file to load"
      },
      df_name: {
        type: "string",
        description: "Name for the DataFrame (optional, defaults to df_1, df_2, etc.)"
      }
    },
    required: ["csv_path"]
  }

• claude_mcp_data_explorer/server.py:74-95 (schema)

  Tool dispatch handler in Python server that routes 'load-csv' calls to the data_loader handler.

  async def handle_call_tool(
      name: str,
      arguments: dict | None
  ) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
      """Handle tool execution"""
      try:
          if name == "load-csv":
              return await handle_load_csv(arguments)
          elif name == "run-script":
              return await handle_run_script(arguments)
          else:
              raise ValueError(f"Unknown tool: {name}")
      except Exception as e:
          error_message = f"Error executing tool {name}: {str(e)}\n{traceback.format_exc()}"
          logging.error(error_message)
          return [
              types.TextContent(
                  type="text",
                  text=f"Error: {str(e)}"
              )
          ]