Plotnine MCP Server

Instructions

Implementation Reference

• src/plotnine_mcp/server.py:499-521 (registration)

  Registration of the batch_create_plots tool, including name, description, and input schema defining an array of plot configurations.

          Tool(
              name="batch_create_plots",
              description="""Create multiple plots in one batch operation.
  
  Useful for:
  - Creating plots for all numeric columns in a dataset
  - Generating pairwise scatter plots
  - Creating plots for each category separately
  - Comparing different plot types
  
  Each plot configuration is processed independently, and all plots are created in sequence.""",
              inputSchema={
                  "type": "object",
                  "properties": {
                      "plots": {
                          "type": "array",
                          "description": "Array of plot configurations (same structure as create_plot)",
                          "items": {"type": "object"},
                      },
                  },
                  "required": ["plots"],
              },
          ),

• src/plotnine_mcp/server.py:1130-1196 (handler)

  The handler function that implements batch_create_plots by iterating over the provided list of plot configurations and delegating to create_plot_handler for each, collecting results and providing a summary.

  async def batch_create_plots_handler(arguments: dict[str, Any]) -> list[TextContent]:
      """Handle batch_create_plots tool calls."""
      try:
          plots = arguments.get("plots", [])
  
          if not plots:
              return [
                  TextContent(
                      type="text",
                      text="No plots provided. Please include an array of plot configurations in the 'plots' parameter.",
                  )
              ]
  
          message = f"Batch Plot Creation\n" + "=" * 60 + "\n\n"
          message += f"Creating {len(plots)} plot(s)...\n\n"
  
          results = []
          successful = 0
          failed = 0
  
          for i, plot_config in enumerate(plots, 1):
              try:
                  # Create plot using existing handler
                  result = await create_plot_handler(plot_config)
  
                  if result and "successfully" in result[0].text:
                      successful += 1
                      # Extract filename from result
                      result_text = result[0].text
                      if "Output file:" in result_text:
                          filename_line = [
                              line for line in result_text.split("\n") if "Output file:" in line
                          ][0]
                          filename = filename_line.split(": ")[1]
                          message += f"{i}. ✓ {filename}\n"
                      else:
                          message += f"{i}. ✓ Plot created\n"
                  else:
                      failed += 1
                      error_msg = result[0].text if result else "Unknown error"
                      message += f"{i}. ✗ Failed: {error_msg[:100]}...\n"
  
                  results.append({"index": i, "success": successful > failed, "result": result})
  
              except Exception as e:
                  failed += 1
                  message += f"{i}. ✗ Error: {str(e)[:100]}...\n"
                  results.append({"index": i, "success": False, "error": str(e)})
  
          message += "\n" + "=" * 60 + "\n"
          message += f"Summary:\n"
          message += f"  • Total: {len(plots)}\n"
          message += f"  • Successful: {successful}\n"
          message += f"  • Failed: {failed}\n"
  
          if successful > 0:
              message += f"\n✓ {successful} plot(s) created successfully!"
  
          return [TextContent(type="text", text=message)]
  
      except Exception as e:
          return [
              TextContent(
                  type="text",
                  text=f"Batch creation error: {str(e)}\n\nPlease check your plot configurations.",
              )
          ]

• src/plotnine_mcp/server.py:510-520 (schema)

  Input schema definition for batch_create_plots, specifying an array of plot configuration objects.

  inputSchema={
      "type": "object",
      "properties": {
          "plots": {
              "type": "array",
              "description": "Array of plot configurations (same structure as create_plot)",
              "items": {"type": "object"},
          },
      },
      "required": ["plots"],
  },