A Model Context Protocol server that enables LLMs to interact with MLflow tracking servers, allowing users to query experiments, analyze runs, compare metrics, manage the model registry, and promote models through natural language.
Compare metrics across multiple MLflow runs to evaluate model performance. Use side-by-side analysis to identify the most effective run for your needs.
Retrieve MLflow runs for an experiment to view metrics, parameters, and status. Filter by criteria such as 'metrics.auc > 0.9' to isolate specific runs.