ML Referee

io.github.scarrico/mlreferee · v1.1.0 · data-and-databases

ML Referee is healthy: it completed an MCP handshake in 1049 ms and exposes 26 tools.

Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.

Endpoint: https://api.mlreferee.com/mcp (streamable-http)

No repository listed · Website · JSON · Add to my inventory

Facts

Users (last 30 days)0
HandshakeHealthy
Auth neededNone
Tool count26
Latency1049 ms
Last checked (UTC)2026-10-27T00:15:07.864Z

Health history

Checked (UTC)StatusLatencyError
2026-10-27T00:15:07.864ZHealthy1049

Tools (26)

describe_refereeDiscover capabilities, privacy, and the approved public catalog.
list_verticalsList the three supported evaluation profiles and their discovery tags.
get_referee_readinessReport connection, credential, audit-credit, and submission readiness with the next action.
get_referee_usageRead aggregate, privacy-preserving Referee activity and outcome evidence for the selected audience.
get_input_schemaGet neutral column roles and validation defaults for a vertical.
get_repair_schemaGet the feature-only contract for diagnosing degradation and testing bounded repairs.
upload_private_datasetEncrypt a de-identified CSV/JSON payload for a short tenant-private retention window.
upload_campaign_shardEncrypt one of up to 64 private feature shards for a large campaign; retain for at least 4,200 seconds.
upload_repair_matrixEncrypt one complete de-identified repair matrix of up to 100 MB and 1,000 diagnostic features.
preflight_datasetValidate a tenant-private upload and its baseline evidence/row identity without spending a credit.
preflight_repairValidate a tenant-private feature-repair matrix without spending a credit.
quote_auditCreate a contract-bound quote for one audit credit; baseline mode and evidence cannot be substituted.
quote_repairPreflight and quote label-based feature repair; large jobs return a measured ETA and credit requirement.
quote_campaignPreflight all private feature shards, time a pilot, and quote credits and ETA for up to 1,000 candidates in one corrected search family.
get_creditsRead beta or paid audit-credit availability and usage.
redeem_beta_inviteRedeem one operator-issued invite for free beta audit credits before January 1, 2027.
request_beta_accessRequest operator-reviewed beta access without purchasing or granting credits.
get_beta_request_statusRead the authenticated tenant's beta-access request status.
submit_auditAccept a quote and atomically reserve its disclosed audit credits.
record_audit_followupRecord whether a completed audit changed a decision or was confirmed prospectively.
get_audit_statusRead the state of an audit owned by the authenticated tenant.
get_audit_resultRead a completed tenant-private result and signed output manifest.
get_audit_receiptRead a tenant-private report fingerprint retained after report expiry or deletion. Older reports may have no record. This does not retrieve report contents.
verify_audit_reportCompare 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
delete_auditDelete retained inputs and results for an audit owned by this tenant.
delete_uploadDelete a tenant-private upload that is no longer needed.