mcpField
M
mcp-server-scikit-learn: MCP server for Scikit-learn

mcp-server-scikit-learn: MCP server for Scikit-learn

Local
github.com/shibuiwilliamData & Analytics18Updated 84w ago
Repository

About mcp-server-scikit-learn: MCP server for Scikit-learn

mcp-server-scikit-learn is an MCP server for developers and data practitioners working with Scikit-learn. It offers a standardized interface for model training, evaluation, dataset preparation, and model persistence.

Key features

  1. 01Train and evaluate models
  2. 02Prepare and preprocess datasets
  3. 03Save and load models
  4. 04Engineer and select features
  5. 05Cross-validation and hyperparameter tuning

Use cases

  1. 01Train and assess Scikit-learn models
  2. 02Preprocess datasets for modeling
  3. 03Tune model parameters with cross-validation

MCP support

The MCP server provides a standardized interface for interacting with Scikit-learn models and datasets, including training, preprocessing, evaluation, and persistence operations.

#mcp-server#scikit-learn#model-context-protocol

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "scikit-learn": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector"
      ]
    }
  }
}
Run commandnpx -y @modelcontextprotocol/inspector

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/inspector

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-server-scikit-learn: MCP server for Scikit-learn

Overview

This is a Model Context Protocol server for Scikit-learn, providing a standardized interface for interacting with Scikit-learn models and datasets.

Features

  • Train and evaluate Scikit-learn models
  • Handle datasets and data preprocessing
  • Model persistence and loading
  • Feature engineering and selection
  • Model evaluation metrics
  • Cross-validation and hyperparameter tuning

Run this project locally

This project is not yet set up for ephemeral environments (e.g. uvx usage). Run this project locally by cloning this repo:

git clone https://github.com/yourusername/mcp-server-scikit-learn.git
cd mcp-server-scikit-learn

You can launch the MCP inspector via npm:

npx @modelcontextprotocol/inspector uv --directory=src/mcp_server_scikit_learn run mcp-server-scikit-learn

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

OR Add this tool as a MCP server:

{
  "scikit-learn": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/mcp-server-scikit-learn",
      "run",
      "mcp-server-scikit-learn"
    ]
  }
}

Development

  1. Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install dependencies:
pip install -e ".[dev]"
  1. Run tests:
pytest -s -v tests/

License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.