MCP App Store
by KeenEthics
ML Referee icon

ML Referee MCP Server for ChatGPT

By Sandra Carrico

Overview

Evaluate up to 1,000 candidate features in one run. ML Referee provides independent evidence for feature selection, bounded model repair, and research prioritization without requiring a separate ablation run per feature. For machine-learning researchers and practitioners working with supervised prediction or forecasting, it checks submitted inputs, runs supported evaluations with user authorization, and retrieves results. Results are evidence within the declared evaluation setup, not guarantees of future performance or deployment readiness. An ML Referee account is required. Access requirements are described on the ML Referee website.

How to connect

  1. ChatGPT: Open the ML Referee listing in the ChatGPT app directory and choose Connect. ChatGPT listing ML Referee exposes 26 tools here.

Tools

delete_audit

ChatGPT
Delete retained inputs and results for an audit owned by this tenant.

delete_upload

ChatGPT
Delete a tenant-private upload that is no longer needed.

describe_referee

ChatGPT
Discover capabilities, privacy, and the approved public catalog.

get_audit_receipt

ChatGPT
Read a tenant-private report fingerprint retained after report expiry or deletion. Older reports may have no record. This does not retrieve report contents.

get_audit_result

ChatGPT
Read a completed tenant-private result and signed output manifest.

get_audit_status

ChatGPT
Read the state of an audit owned by the authenticated tenant.

get_beta_request_status

ChatGPT
Read the authenticated tenant's beta-access request status.

get_credits

ChatGPT
Read beta or paid audit-credit availability and usage.

get_input_schema

ChatGPT
Get neutral column roles and validation defaults for a vertical.

get_referee_readiness

ChatGPT
Report connection, credential, audit-credit, and submission readiness with the next action.

get_referee_usage

ChatGPT
Read aggregate, privacy-preserving Referee activity and outcome evidence for the selected audience.

get_repair_schema

ChatGPT
Get the feature-only contract for diagnosing degradation and testing bounded repairs.

list_verticals

ChatGPT
List the three supported evaluation profiles and their discovery tags.

preflight_dataset

ChatGPT
Validate a tenant-private upload and its baseline evidence/row identity without spending a credit.

preflight_repair

ChatGPT
Validate a tenant-private feature-repair matrix without spending a credit.

quote_audit

ChatGPT
Create a contract-bound quote for one audit credit; baseline mode and evidence cannot be substituted.

quote_campaign

ChatGPT
Preflight all private feature shards, time a pilot, and quote credits and ETA for up to 1,000 candidates in one corrected search family.

quote_repair

ChatGPT
Preflight and quote label-based feature repair; large jobs return a measured ETA and credit requirement.

record_audit_followup

ChatGPT
Record whether a completed audit changed a decision or was confirmed prospectively.

redeem_beta_invite

ChatGPT
Redeem one operator-issued invite for free beta audit credits before January 1, 2027.

request_beta_access

ChatGPT
Request operator-reviewed beta access without purchasing or granting credits.

submit_audit

ChatGPT
Accept a quote and atomically reserve its disclosed audit credits.

upload_campaign_shard

ChatGPT
Encrypt one of up to 64 private feature shards for a large campaign; retain for at least 4,200 seconds.

upload_private_dataset

ChatGPT
Encrypt a de-identified CSV/JSON payload for a short tenant-private retention window.

upload_repair_matrix

ChatGPT
Encrypt one complete de-identified repair matrix of up to 100 MB and 1,000 diagnostic features.

verify_audit_report

ChatGPT
Compare a locally computed SHA-256 with the retained tenant-private receipt. Use the exact downloaded result JSON bytes (not the API envelope), or UTF-8 result.report text with representation report_text. Never copy the expected hash as the candidate: compute it from the supplied artifact. A digest match does not validate a summary, factual correctness, or absence of harm. No report is uploaded.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/ml-referee"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/ml-referee)