Metadata-Version: 2.4
Name: ml-trainer-mcp
Version: 0.2.0
Summary: An MCP server that trains and evaluates machine learning models through MCP tools
Keywords: mcp,machine-learning,scikit-learn,llm,ai
Author: Abhijith BR
Author-email: Abhijith BR <abhijithofical@gmail.com>
License-Expression: MIT
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Dist: mcp[cli]>=1.2.0
Requires-Dist: pandas>=2.0.0
Requires-Dist: scikit-learn>=1.4.0
Requires-Dist: numpy>=1.26.0
Requires-Dist: matplotlib>=3.8.0
Requires-Dist: seaborn>=0.13.0
Requires-Python: >=3.10
Project-URL: Homepage, https://github.com/AbhijithB-R/ml-trainer-mcp
Project-URL: Repository, https://github.com/AbhijithB-R/ml-trainer-mcp
Project-URL: Issues, https://github.com/AbhijithB-R/ml-trainer-mcp/issues
Description-Content-Type: text/markdown

# ML Trainer MCP

An MCP server that trains and evaluates machine learning models through MCP tools.

## Quickstart

```bash
uv pip install -e .
uv run ml-trainer-mcp
```

Or test interactively with the MCP Inspector:

```bash
mcp dev src/ml_trainer_mcp/server.py
```

## Tools

| Tool | Description |
|---|---|
| `load_csv(path)` | Load a CSV file as the active dataset |
| `dataset_info()` | Shape, dtypes, and summary stats |
| `list_columns()` | List column names |
| `missing_values()` | Report missing values per column |
| `train_linear_regression(target)` | Train a linear regression model |
| `train_random_forest(target, ...)` | Train a random forest regressor |
| `evaluate_model(test_size)` | Evaluate the trained model on a held-out split |
| `predict(input_data)` | Predict on a single new row |
| `feature_importance()` | Feature importances / coefficients |