Datawrapper MCP

Instructions

Implementation Reference

• handlers/publish.py:11-28 (handler)

  The actual handler function implementing the publish_chart tool logic.

  async def publish_chart(arguments: PublishChartArgs) -> list[TextContent]:
      """Publish a chart to make it publicly accessible."""
      chart_id = arguments["chart_id"]
  
      # Get chart and publish using Pydantic instance method
      chart = get_chart(chart_id)
      chart.publish()
  
      public_url = chart.get_public_url()
  
      result = {
          "chart_id": chart_id,
          "public_url": public_url,
          "message": "Chart published successfully!",
      }
  
      return [TextContent(type="text", text=json.dumps(result, indent=2))]

• server.py:224-247 (registration)

  The MCP tool decorator and wrapper for publishing a chart.

  async def publish_chart(chart_id: str) -> str:
      """⚠️ DATAWRAPPER MCP TOOL ⚠️
      This is part of the Datawrapper MCP server integration.
  
      ---
  
      Publish a Datawrapper chart to make it publicly accessible.
      Returns the public URL of the published chart.
      IMPORTANT: Only use this tool when the user explicitly requests to publish the chart.
      Do not automatically publish charts after creation unless specifically asked.
  
      Args:
          chart_id: ID of the chart to publish
  
      Returns:
          Public URL of the published chart
      """
      try:
          arguments = cast(PublishChartArgs, {"chart_id": chart_id})
          result = await publish_chart_handler(arguments)
          return result[0].text
      except Exception as e:
          return f"Error publishing chart with ID '{chart_id}': {str(e)}"

• dw_types.py:28-32 (schema)

  Type definition for the arguments accepted by the publish_chart tool.

  class PublishChartArgs(TypedDict):
      """Arguments for publish_chart handler."""
  
      chart_id: str