No user-submitted related servers found.
Scored across 9 tools
Each tool maps to a distinct pipeline stage (train, predict, evaluate, select, explain, export), and predict_both is clearly described as a convenience wrapper over the two single-model predict tools. The only mild overlap is predict_both versus predict_logistic_regression/predict_knn, but the descriptions make the distinction explicit.
Most names follow a readable snake_case verb_noun pattern (train_models, get_sample_input, predict_knn, select_best_model, export_parquet_audit). A couple deviate in ordering or form (shap_explain_selected is noun-first, confusion_matrix_metrics is noun-only), but the set remains predictable.
Nine tools is well-scoped for an end-to-end ML demo pipeline, and each one covers a distinct stage with no filler. Nothing feels redundant or missing at the count level.
The surface covers the full lifecycle: train, sample input, per-model prediction, combined prediction, evaluation metrics, model selection, SHAP explanation, and audit export. Minor gaps exist (no tool to inspect dataset/artifact status or list available models before predicting), but agents can work around these via train_models and get_sample_input.