MCP Machine Learning Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| train_modelsB | Train Logistic Regression and KNN on the breast cancer dataset and export joblib artifacts. |
| get_sample_inputA | Return one test-set patient as a ready-to-use |
| predict_logistic_regressionB | Predict malignant (0) or benign (1) using the saved Logistic Regression model. |
| predict_knnA | Predict malignant (0) or benign (1) using the saved KNN model. |
| confusion_matrix_metricsA | Compute the confusion matrix plus accuracy/precision/recall for both models on the test set. Precision and recall are for the malignant class. Confusion matrix order is [malignant, benign]; rows = actual, columns = predicted. |
| select_best_modelB | Select the best model using a rule (default: recall, then precision, then accuracy). |
| shap_explain_selectedB | Run SHAP for the selected model: global top features plus a local explanation for one test row. Positive SHAP values push toward malignant. |
| export_parquet_auditB | Export a copy of the Parquet audit log for submission. |
| predict_bothA | Predict with BOTH models in one call and report whether they agree. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have a crisp, distinct role (train, predict per model, evaluate, select, explain, export). The only overlap is predict_both versus predict_logistic_regression/predict_knn, but its description clearly frames it as a convenience wrapper that also reports agreement, so misselection risk is low.
Names are uniformly snake_case and mostly verb-first (train_models, predict_knn, select_best_model, get_sample_input, export_parquet_audit). The lone deviation is the noun-first confusion_matrix_metrics, and shap_explain_selected stacks verbs, but both remain readable and predictable.
Nine tools map cleanly onto a single ML workflow (train → sample input → predict → evaluate → select → explain → export), with no padding. This is squarely in the well-scoped 3-15 range.
The surface covers the full lifecycle: training, per-model and combined prediction, metrics, model selection, SHAP explanation, and audit export. Minor gaps exist around inspecting or listing saved model artifacts and resetting/retraining with custom configuration, but agents can work around these via train_models.