vizro-mcp

Instructions

If successful, the tool will return the python code and, if it is a remote file, the py.cafe link to the chart.
The PyCafe link will be automatically opened in your default browser if auto_open is True.

Returns:
    ValidationResults object with status and dashboard details

Implementation Reference

• vizro-mcp/src/vizro_mcp/server.py:245-306 (handler)

  The core handler function for the 'validate_dashboard_config' tool. Decorated with @mcp.tool(), it validates the provided dashboard configuration using Vizro's model_validate, handles custom charts, generates Python code and optional PyCafe preview link, and opens the browser if specified.

  @mcp.tool()
  def validate_dashboard_config(
      dashboard_config: dict[str, Any] = Field(
          description="Either a JSON string or a dictionary representing a Vizro dashboard model configuration"
      ),
      data_infos: list[DFMetaData] = Field(
          description="List of DFMetaData objects containing information about the data files"
      ),
      custom_charts: list[ChartPlan] = Field(
          description="List of ChartPlan objects containing information about the custom charts in the dashboard"
      ),
      auto_open: bool = Field(default=True, description="Whether to automatically open the PyCafe link in a browser"),
  ) -> ValidateResults:
      """Validate Vizro model configuration. Run ALWAYS when you have a complete dashboard configuration.
  
      If successful, the tool will return the python code and, if it is a remote file, the py.cafe link to the chart.
      The PyCafe link will be automatically opened in your default browser if auto_open is True.
  
      Returns:
          ValidationResults object with status and dashboard details
      """
      Vizro._reset()
  
      try:
          dashboard = vm.Dashboard.model_validate(
              dashboard_config,
              context={"allow_undefined_captured_callable": [custom_chart.chart_name for custom_chart in custom_charts]},
          )
      except ValidationError as e:
          return ValidateResults(
              valid=False,
              message=f"""Validation Error: {e!s}. Fix the error and call this tool again.
  Calling `get_model_json_schema` may help.""",
              python_code="",
              pycafe_url=None,
              browser_opened=False,
          )
  
      else:
          code_link = get_python_code_and_preview_link(dashboard, data_infos, custom_charts)
  
          pycafe_url = code_link.pycafe_url if all(info.file_location_type == "remote" for info in data_infos) else None
          browser_opened = False
  
          if pycafe_url and auto_open:
              try:
                  browser_opened = webbrowser.open(pycafe_url)
              except Exception:
                  browser_opened = False
  
          return ValidateResults(
              valid=True,
              message="""Configuration is valid for Dashboard! Do not forget to call this tool again after each iteration.
  If you are creating an `app.py` file, you MUST use the code from the validation tool, do not modify it, watch out for
  differences to previous `app.py`""",
              python_code=code_link.python_code,
              pycafe_url=pycafe_url,
              browser_opened=browser_opened,
          )
  
      finally:
          Vizro._reset()

• vizro-mcp/src/vizro_mcp/server.py:44-52 (schema)

  Pydantic-style dataclass defining the output schema for the validate_dashboard_config tool (and similar validation tools), including validation status, error/success message, generated Python code, PyCafe URL, and browser open status.

  @dataclass
  class ValidateResults:
      """Results of validation tools."""
  
      valid: bool
      message: str
      python_code: str
      pycafe_url: str | None
      browser_opened: bool