optuna-mcp
optuna-mcp is an MCP server. Its repository has 88 GitHub stars and is licensed under MIT; we last read it on 2026-10-22.
This server acts as an MCP server to interact with Optuna APIs.
Install
Read from optuna-mcp’s own README, close to verbatim -- not written by us, and not guessed.
pip install optuna-mcp
What it reaches, and what it needs
Reaches
○ not recognised
Credential
○ none found
Maintenance
Stars
88
State
listed
Licence
MIT
From the repository
The Optuna MCP Server is a Model Context Protocol (MCP) server to interact with Optuna APIs.
What optuna-mcp can do
22 tools documented in its README. An AI client calls these by name.
create_study- Create a new Optuna study with the given study_name and directions.
set_sampler- Set the sampler for the study.
get_all_study_names- Get all study names from the storage.
set_metric_names- Set metric_names. Metric_names are labels used to distinguish what each objective value is.
get_metric_names- Get metric_names.
get_directions- Get the directions of the study.
get_trials- Get all trials in a CSV format.
best_trial- Get the best trial.
best_trials- Return trials located at the Pareto front in the study.
set_trial_user_attr- Set user attributes for a trial.
get_trial_user_attrs- Get user attributes in a trial.
plot_optimization_history- Return the optimization history plot as an image.
plot_hypervolume_history- Return the hypervolume history plot as an image.
plot_pareto_front- Return the Pareto front plot as an image for multi-objective optimization.
plot_contour- Return the contour plot as an image.
plot_parallel_coordinate- Return the parallel coordinate plot as an image.
plot_slice- Return the slice plot as an image.
plot_param_importances- Return the parameter importances plot as an image.
plot_edf- Return the EDF plot as an image.
plot_timeline- Return the timeline plot as an image.
plot_rank- Return the rank plot as an image.
launch_optuna_dashboard- Launch the Optuna dashboard.
Read from the README; names are kept only if the README contains them.
Common questions about optuna-mcp
- What does optuna-mcp do?
- This server acts as an MCP server to interact with Optuna APIs.
- How do I install optuna-mcp?
- Its own README gives this command: pip install optuna-mcp. Run it where your MCP client can launch the server, and check the README for any settings it asks for.
- Is optuna-mcp official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 88 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-22.
- What licence does optuna-mcp use?
- The repository declares the MIT licence.