78trust / 100

ML Referee

by mlreferee.com in Developer tools

MCP serverPassing, checked 11 h ago

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

https://api.mlreferee.com/mcp
Tools
26
open to any client
Uptime
100%
last 30 days
Response time
612 ms
669 ms slowest 5%
Last check
Passed
11 h ago, next any minute now

Scan it nowHow to connect

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to connect

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "ml-referee": {
      "type": "http",
      "url": "https://api.mlreferee.com/mcp"
    }
  }
}

26 tools

  • describe_referee

    Discover capabilities, privacy, and the approved public catalog.

  • list_verticals

    List the three supported evaluation profiles and their discovery tags.

  • get_referee_readiness

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

  • get_referee_usage

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

  • get_input_schema

    Get neutral column roles and validation defaults for a vertical.

  • get_repair_schema

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

  • upload_private_dataset

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

  • upload_campaign_shard

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

  • upload_repair_matrix

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

  • preflight_dataset

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

  • preflight_repair

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

  • quote_audit

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

  • quote_repair

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

  • quote_campaign

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

  • get_credits

    Read beta or paid audit-credit availability and usage.

  • redeem_beta_invite

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

  • request_beta_access

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

  • get_beta_request_status

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

  • submit_audit

    Accept a quote and atomically reserve its disclosed audit credits.

  • record_audit_followup

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

  • get_audit_status

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

  • get_audit_result

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

  • get_audit_receipt

    Read 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_report

    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…

  • delete_audit

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

  • delete_upload

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

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
11 h agoPassed200602 ms
22 h agoPassed200592 ms
33 h agoPassed200666 ms
47 h agoPassed200655 ms
3 days agoPassed200662 ms
Show 10 older checks
3 days agoPassed200669 ms
4 days agoPassed200603 ms
4 days agoPassed200606 ms
5 days agoPassed200631 ms
6 days agoPassed200598 ms
6 days agoPassed200644 ms
6 days agoPassed200612 ms
7 days agoPassed200661 ms
8 days agoPassed200594 ms
8 days agoPassed200603 ms