ML Referee
REMOTE · API.MLREFEREE.COM
Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.
Available components
Last scanned (19 hours ago)
Scores higher than 44% of remote servers
Reachable. Last reached 4 Nov 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_audit). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability56
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 1051 tokens (~40/item across 26 items; 26 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 26 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
- Stability: unverified → 0.03 ▲ functional
- 27 Oct 26 58
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://api.mlreferee.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.mlreferee.com | CN=YE2,O=Let's Encrypt,C=US | 17 Oct 2026 | 15 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 6b270352cee633f6c80e94bfe3e78281e2b |
| SANs: api.mlreferee.com | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.mlreferee.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| mlreferee.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| content-security-policy | default-src 'none'; frame-ancestors 'none' |
| x-content-type-options | nosniff |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.mlreferee.com/mcp | Verified | 200 | |
| http (plaintext) | http://api.mlreferee.com/mcp | HTTPS enforced | 308 | https://api.mlreferee.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
delete_audit ~30
Delete retained inputs and results for an audit owned by this tenant.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string | yes | – |
No output schema declared.
No examples provided.
delete_upload ~27
Delete a tenant-private upload that is no longer needed.
| Name | Type | Req | Description |
|---|---|---|---|
| upload_id | string | yes | – |
No output schema declared.
No examples provided.
describe_referee ~20
Discover capabilities, privacy, and the approved public catalog.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_audit_receipt ~46
Read a tenant-private report fingerprint retained after report expiry or deletion. Older reports may have no record. This does not retrieve report contents.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string | yes | – |
No output schema declared.
No examples provided.
get_audit_result ~29
Read a completed tenant-private result and signed output manifest.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string | yes | – |
No output schema declared.
No examples provided.
get_audit_status ~30
Read the state of an audit owned by the authenticated tenant.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string | yes | – |
No output schema declared.
No examples provided.
get_beta_request_status ~28
Read the authenticated tenant's beta-access request status.
| Name | Type | Req | Description |
|---|---|---|---|
| request_id | string | yes | – |
No output schema declared.
No examples provided.
get_credits ~19
Read beta or paid audit-credit availability and usage.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_input_schema ~27
Get neutral column roles and validation defaults for a vertical.
| Name | Type | Req | Description |
|---|---|---|---|
| vertical | string | yes | – |
No output schema declared.
No examples provided.
get_referee_readiness ~27
Report connection, credential, audit-credit, and submission readiness with the next action.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_referee_usage ~35
Read aggregate, privacy-preserving Referee activity and outcome evidence for the selected audience.
| Name | Type | Req | Description |
|---|---|---|---|
| window_days | integer | – | – |
No output schema declared.
No examples provided.
get_repair_schema ~23
Get the feature-only contract for diagnosing degradation and testing bounded repairs.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_verticals ~20
List the three supported evaluation profiles and their discovery tags.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
preflight_dataset ~46
Validate a tenant-private upload and its baseline evidence/row identity without spending a credit.
| Name | Type | Req | Description |
|---|---|---|---|
| contract | – | yes | – |
| upload_id | string | yes | – |
| vertical | string | yes | – |
No output schema declared.
No examples provided.
preflight_repair ~36
Validate a tenant-private feature-repair matrix without spending a credit.
| Name | Type | Req | Description |
|---|---|---|---|
| contract | – | yes | – |
| upload_id | string | yes | – |
No output schema declared.
No examples provided.
quote_audit ~57
Create a contract-bound quote for one audit credit; baseline mode and evidence cannot be substituted.
| Name | Type | Req | Description |
|---|---|---|---|
| contract | – | yes | – |
| idempotency_key | string | yes | – |
| upload_id | string | yes | – |
| vertical | string | yes | – |
No output schema declared.
No examples provided.
quote_campaign ~62
Preflight all private feature shards, time a pilot, and quote credits and ETA for up to 1,000 candidates in one corrected search family.
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | yes | – |
| shards | array | yes | – |
| vertical | string | yes | – |
No output schema declared.
No examples provided.
quote_repair ~51
Preflight and quote label-based feature repair; large jobs return a measured ETA and credit requirement.
| Name | Type | Req | Description |
|---|---|---|---|
| contract | – | yes | – |
| idempotency_key | string | yes | – |
| upload_id | string | yes | – |
No output schema declared.
No examples provided.
record_audit_followup ~47
Record whether a completed audit changed a decision or was confirmed prospectively.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string | yes | – |
| kind | string | yes | – |
| value | string | yes | – |
No output schema declared.
No examples provided.
redeem_beta_invite ~38
Redeem one operator-issued invite for free beta audit credits before January 1, 2027.
| Name | Type | Req | Description |
|---|---|---|---|
| invite_code | string | yes | – |
No output schema declared.
No examples provided.
request_beta_access ~45
Request operator-reviewed beta access without purchasing or granting credits.
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | yes | – |
| lane | string | yes | – |
| use_case | string | yes | – |
No output schema declared.
No examples provided.
submit_audit ~39
Accept a quote and atomically reserve its disclosed audit credits.
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | yes | – |
| quote_id | string | yes | – |
No output schema declared.
No examples provided.
upload_campaign_shard ~57
Encrypt one of up to 64 private feature shards for a large campaign; retain for at least 4,200 seconds.
| Name | Type | Req | Description |
|---|---|---|---|
| data | string | yes | – |
| format | string | – | – |
| retention_seconds | integer | – | – |
No output schema declared.
No examples provided.
upload_private_dataset ~48
Encrypt a de-identified CSV/JSON payload for a short tenant-private retention window.
| Name | Type | Req | Description |
|---|---|---|---|
| data | string | yes | – |
| format | string | – | – |
| retention_seconds | integer | – | – |
No output schema declared.
No examples provided.
upload_repair_matrix ~54
Encrypt one complete de-identified repair matrix of up to 100 MB and 1,000 diagnostic features.
| Name | Type | Req | Description |
|---|---|---|---|
| data | string | yes | – |
| format | string | – | – |
| retention_seconds | integer | – | – |
No output schema declared.
No examples provided.
verify_audit_report ~110
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.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string | yes | – |
| representation | string | – | – |
| sha256 | string | yes | – |
No output schema declared.
No examples provided.
How do I install the ML Referee MCP server?
ML Referee is a hosted endpoint at https://api.mlreferee.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.mlreferee.com
claude mcp add --transport http scarrico-mlreferee 'https://api.mlreferee.com/mcp'
What is the ML Referee MCP server?
ML Referee is an MCP server listed in the public MCP registry as io.github.scarrico/mlreferee. Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta. This page covers its hosted endpoint (https://api.mlreferee.com/mcp).
Is the ML Referee MCP server safe to use?
ML Referee scores 62 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ML Referee MCP server expose?
ML Referee exposes 26 tools: describe_referee, list_verticals, get_referee_readiness, get_referee_usage, get_input_schema, and 21 more. Their descriptions and schemas cost roughly 1,051 tokens of context every time the server is loaded.
Does the ML Referee MCP server require authentication?
No. We connected to ML Referee without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the ML Referee MCP server still maintained?
ML Referee is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.