{"mcpName":"station__algovigilance__microgram-ml-pipeline-ml-evaluate","slug":"algovigilance__microgram-ml-pipeline-ml-evaluate","label":"Microgram: ml-pipeline-ml-evaluate","description":"Evaluate a trained ML model on held-out test data. Returns AUC-ROC, precision, recall, F1 score, accuracy, and confusion matrix (TN/FP/FN/TP).","domainSlug":"algovigilance","pvRelevance":"pv-core","backend":"native","agentMetadata":{"idempotent":true,"read_only":true,"expected_latency_ms":null,"cost_tokens_estimate":null,"pipes_to":null},"inputSchema":{"type":"object","properties":{"model_id":{"type":"string","description":"Model ID to evaluate."},"test_samples":{"type":"object","description":"Test samples with labels."}},"required":["model_id","test_samples"],"additionalProperties":false},"example":null,"taxonomy":{"rank":{"domain":"Substrata","kingdom":"Constructa","phylum":"Configa","class":"station-config","order":"algovigilance","family":"mcp-tool-config"},"characteristics":{"substrate":"config","domain":"pv","lifecycle":"continuous","stateful":false,"persistence":"none","authority":"read","compounding":"producer","io_input":"agent-request","io_output":"tool-response"}},"_links":{"html":"/tools/algovigilance__microgram-ml-pipeline-ml-evaluate","markdown":"/tools/algovigilance__microgram-ml-pipeline-ml-evaluate/raw.md","invoke":"/api/mcp","catalog":"/api/mcp"}}