Mcp Proxyml MCP Server

MCP server for the ProxyML API. Gives Claude (and other MCP clients) direct access to ProxyML's surrogate modelling and explainability tools.

Local server

What is the Mcp Proxyml MCP Server?

Mcp Proxyml is an MCP project maintained in the proxyml/mcp-proxyml repository. The maintainer describes its purpose as “MCP server for the ProxyML API. Gives Claude (and other MCP clients) direct access to ProxyML's surrogate modelling and explainability tools”. Read the project documentation for the complete scope.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
proxyml_infer_schema	Infer a feature schema from a local CSV file — no data sent to the server
proxyml_get_schema	Retrieve a stored schema by name
proxyml_put_schema	Upload or replace a feature schema
proxyml_list_schemas	List all named feature schemas for the authenticated account
proxyml_delete_schema	Delete a named feature schema
proxyml_synthesize_data	Generate synthetic samples from the stored schema
proxyml_train_surrogate	Train a linear surrogate on samples scored by your model
proxyml_list_surrogates	List trained surrogate models, newest first
proxyml_get_model_schema	Retrieve the feature schema snapshotted when a surrogate was trained
proxyml_update_surrogate	Rename or annotate a surrogate without retraining
proxyml_delete_surrogate	Delete a surrogate model by its UUID
proxyml_predict	Get a surrogate prediction for a single instance
proxyml_predict_batch	Get surrogate predictions for a list of instances
proxyml_train_challenger	Train a challenger model locally on a CSV and assemble an upload-ready payload
proxyml_score_champion	Score a champion model's predictions locally, for an apples-to-apples comparison
proxyml_get_summary	Feature importances and model summary
proxyml_export_surrogate	Full coefficient export for audit and governance
proxyml_explain_local	Per-feature contribution breakdown for a single instance
proxyml_explain_local_batch	Per-feature contributions for multiple instances in one call
proxyml_find_counterfactual	Find the nearest point that flips the prediction
proxyml_find_counterfactuals	Batch version of proxyml_find_counterfactual for multiple instances
proxyml_diff_models	Compare feature importances between two surrogate versions
proxyml_detect_drift	Compare two versions and return a structured pass/fail against coefficient and fidelity thresholds
proxyml_get_usage	Current tier, request count, and quota — useful as a pre-flight check
proxyml_health_check	Check API connectivity — no authentication required, doesn't count against usage quota