A
licenseNot graded
qualityC
maintenanceEnables training and comparing logistic regression and KNN models, generating predictions and SHAP explanations, selecting a best model, and exporting Parquet audit logs through MCP tools.
GPL 3.0
MCP Machine Learning Agent
Related Servers
Alternatives to MCP Machine Learning Agent
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables training and comparing Logistic Regression and KNN models, making predictions, selecting the best model, generating SHAP explanations, and exporting Parquet audit logs through MCP tools.GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables training and comparing Logistic Regression and KNN classifiers, generating predictions, confusion-matrix metrics, model selection, SHAP explanations, and Parquet audit exports through MCP tools.GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables training and comparing logistic regression and KNN models, retrieving sample patient inputs, generating predictions and confusion-matrix metrics, selecting the best model, producing SHAP explanations, and exporting Parquet audit logs through MCP tools.GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables users to train, evaluate, select, explain, and use logistic regression and KNN models through MCP tools, including sample input retrieval, predictions, confusion-matrix metrics, SHAP explanations, and Parquet audit export.GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables users to train, evaluate, select, and explain Logistic Regression and KNN models through MCP tools, including predictions, SHAP explanations, and Parquet audit logging.GPL 3.0
TDQS
A3.7/5.0
Scored across 9 tools
Disambiguation4/5
Most tools have clearly distinct purposes: training, sample input, individual predictions, metrics, model selection, SHAP explanation, and audit export. Minor overlap exists between predict_both and the individual predict tools, and between confusion_matrix_metrics and select_best_model, but descriptions make the intended use clear.
Naming Consistency4/5
All names use snake_case consistently, and most follow a verb_noun or verb_object pattern. A few deviate, such as confusion_matrix_metrics (noun phrase) and shap_explain_selected (awkward ordering), but the overall convention is predictable.
Tool Count5/5
Nine tools are well-scoped for a compact ML workflow: training, sample retrieval, two predictions plus a combined prediction, evaluation, selection, explanation, and audit export. Each tool has a clear role without excessive surface area.
Completeness5/5
The surface covers the full workflow from training and sample input through prediction, evaluation, model selection, explainability, and audit export. There are no obvious dead ends for the stated breast-cancer-dataset ML-agent purpose.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues