Optuna MCP Server

AModel Context Protocol (MCP)server that automates optimization and analysis usingOptuna.

Before starting the installation process, installuvfromAstral.

{ "mcpServers": { "Optuna": { "command": "/path/to/uvx", "args": [ "optuna-mcp" ] } } }

Additionally, you can specify the Optuna storage with the--storageargument to persist the results.

{ "mcpServers": { "Optuna": { "command": "/path/to/uvx", "args": [ "optuna-mcp", "--storage", "sqlite:///optuna.db" ] } } }

After adding this, please restart Claude Desktop application. For more information about Claude Desktop, check outthe quickstart page.

{ "mcpServers": { "Optuna": { "command": "docker", "args": [ "run", "-i", "--rm", "--net=host", "-v", "/PATH/TO/LOCAL/DIRECTORY/WHICH/INCLUDES/DB/FILE:/app/workspace", "ghcr.io/optuna/optuna-mcp:latest", "--storage", "sqlite:////app/workspace/optuna.db" ] } } }

The Optuna MCP provides the following tools. Specifically, it offers primitive functions of Optuna such as Study, Trial, Visualization, and Dashboard. Since MCP clients know the list of tools and the details of each tool, users do not need to remember those details.

- create_study- Create a new Optuna study with the given study_name and directions. If the study already exists, it will be simply loaded.

- study_name: name of the study (string, required).
- directions: The directions of optimization (list of literal strings minimize/maximize, optional).

- name: the name of the sampler (string, required).

- metric_names: The list of metric names for each objective (list of strings, required).

- ask- Suggest new parameters using Optuna.

- search_space: the search space for Optuna (dictionary, required).

- trial_number: the trial number (integer, required).
- values: the result of the trial (float or list of floats, required).

- trial_number: the trial number (integer, required).
- key: the key of the user attribute (string, required).
- value: the value of the user attribute (any type, required).

- trial_number: the trial number (integer, required).

- plot_optimization_history- Return the optimization history plot as an image.

- target: index to specify which value to display (integer, optional).
- target_name: target’s name to display on the axis label (string, optional).

- reference_point: a list of reference points to calculate the hypervolume (list of floats, required).

- target_names: objective name list used as the axis titles (list of strings, optional).
- include_dominated_trials: a flag to include all dominated trial's objective values (boolean, optional).
- targets: a list of indices to specify the objective values to display. (list of integers, optional).

- params: parameter list to visualize (list of strings, optional).
- target: an index to specify the value to display (integer, required).
- target_name: target’s name to display on the color bar (string, required).

- params: parameter list to visualize (list of strings, optional).
- target: an index to specify the value to display (integer, required).
- target_name: target’s name to display on the axis label and the legend (string, required).

- params: parameter list to visualize (list of strings, optional).
- target: an index to specify the value to display (integer, required).
- target_name: target’s name to display on the axis label (string, required).

- params: parameter list to visualize (list of strings, optional).
- target: an index to specify the value to display (integer/null, optional).
- target_name: target’s name to display on the legend (string, required).

- target: an index to specify the value to display (integer, required).
- target_name: target’s name to display on the axis label (string, required).

- params: parameter list to visualize (list of strings, optional).
- target: an index to specify the value to display (integer, required).
- target_name: target’s name to display on the color bar (string, required).

- launch_optuna_dashboard- Launch the Optuna dashboard.

- port: server port (integer, optional, default: 58080).

Here we present a simple example of optimizing the 2D-Sphere function, along with example prompts and the summary of the LLM responses.

Starting the Optuna Dashboard and Analyzing Optimization Results

You can also start theOptuna dashboardvia the MCP server to analyze the optimization results interactively.

Check outexamples/auto-matplotlibfor details.

Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB