No user-submitted related servers found.
Scored across 9 tools
Most tools target clearly distinct lifecycle steps: training, sampling input, per-model prediction, combined prediction, evaluation, selection, explainability, and audit export. The only mild overlap is between predict_knn/predict_logistic_regression and predict_both, but the descriptions make the distinction (single model vs. both-plus-agreement) clear enough.
The set is uniformly snake_case and largely verb_noun (predict_knn, train_models, select_best_model, export_parquet_audit). However, confusion_matrix_metrics has no verb and shap_explain_selected uses an inverted/noun-first ordering, breaking the otherwise predictable pattern.
Nine tools is well-scoped for an ML agent covering train, predict, evaluate, select, explain, and export. Each tool earns its place with no filler or redundant entries.
The surface covers the full workflow: training, sample input retrieval, inference (per-model and combined), metrics, model selection, SHAP explanation, and audit export. Minor gaps exist, such as listing or inspecting saved model artifacts/metadata, but agents can work around these.