MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

ML Referee

By scarrico

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

WebsiteSource code
Connect to ML Referee
Checks passed
11 / 22

3 failed · 8 not measured

Median response
727 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
26

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
310
Publisher identityCan the publisher be traced to its source?
222

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 727 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name Referee.

  • Pass
    Lists tools

    tools/list returned 26 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 727 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 727 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Fail
    Parameters documented

    0 of 44 parameters have a description (0%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Fail
    Repo owner matches

    The GitHub repository owner does not match the namespace login.

  • Pass
    Recently updated

    Updated 2026-10-26T23:26:17.751876Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using ML Referee

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http ml-referee https://api.mlreferee.com/mcp

Capabilities

Tools 26

delete_audit

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

Discovered
delete_upload

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

Discovered
describe_referee

Discover capabilities, privacy, and the approved public catalog.

Discovered
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.

Discovered
get_audit_result

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

Discovered
get_audit_status

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

Discovered
get_beta_request_status

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

Discovered
get_credits

Read beta or paid audit-credit availability and usage.

Discovered
get_input_schema

Get neutral column roles and validation defaults for a vertical.

Discovered
get_referee_readiness

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

Discovered
get_referee_usage

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

Discovered
get_repair_schema

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

Discovered
list_verticals

List the three supported evaluation profiles and their discovery tags.

Discovered
preflight_dataset

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

Discovered
preflight_repair

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

Discovered
quote_audit

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

Discovered
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.

Discovered
quote_repair

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

Discovered
record_audit_followup

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

Discovered
redeem_beta_invite

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

Discovered
request_beta_access

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

Discovered
submit_audit

Accept a quote and atomically reserve its disclosed audit credits.

Discovered
upload_campaign_shard

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

Discovered
upload_private_dataset

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

Discovered
upload_repair_matrix

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

Discovered
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 supplied artifact. A digest match does not validate a summary, factual correctness, or absence of harm. No report is uploaded.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected727 ms26

Related servers

All alternatives

Same function and industry, ranked by checks passed then median latency.

Explore alternatives to ML Referee