Skip to main content
Glama

plot_hypervolume_history

Generate a hypervolume history plot to visualize optimization performance based on specified reference points, enabling analysis of multi-objective optimization results.

Instructions

Return the hypervolume history plot as an image.

Args: reference_point: A list of reference points to calculate the hypervolume.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reference_pointYes

Implementation Reference

  • The main handler function for the 'plot_hypervolume_history' tool. It uses Optuna's built-in visualization to generate a hypervolume history plot based on the provided reference point and returns it as a PNG image via MCP's Image type.
    @mcp.tool() def plot_hypervolume_history( reference_point: list[float], ) -> Image: """Return the hypervolume history plot as an image. Args: reference_point: A list of reference points to calculate the hypervolume. """ fig = optuna.visualization.plot_hypervolume_history( mcp.study, reference_point=reference_point, ) return Image(data=plotly.io.to_image(fig), format="png")
  • The @mcp.tool() decorator registers this function as the 'plot_hypervolume_history' MCP tool within the register_tools function.
    @mcp.tool() def plot_hypervolume_history( reference_point: list[float], ) -> Image: """Return the hypervolume history plot as an image. Args: reference_point: A list of reference points to calculate the hypervolume. """ fig = optuna.visualization.plot_hypervolume_history( mcp.study, reference_point=reference_point, ) return Image(data=plotly.io.to_image(fig), format="png")
  • Input schema defined by function signature: reference_point as list[float]. Output is Image.
    def plot_hypervolume_history( reference_point: list[float],

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/optuna/optuna-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server