MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
ML Referee is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
26
tools declared
remote
at its publisher
—
calls last 7d
What it does
Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http ml-referee-mcp https://api.mlreferee.com/mcp
# 2 — ask your agent for something these tools do
# describe_referee, list_verticals, get_referee_readiness and 23 more
ML Referee costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SCAll 1 server
scarrico1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http ml-referee-mcp https://api.mlreferee.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
26 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Discover capabilities, privacy, and the approved public catalog.
No parameter schema on file.
List the three supported evaluation profiles and their discovery tags.
No parameter schema on file.
Report connection, credential, audit-credit, and submission readiness with the next action.
No parameter schema on file.
Read aggregate, privacy-preserving Referee activity and outcome evidence for the selected audience.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| window_days | integer | no | — |
Get neutral column roles and validation defaults for a vertical.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vertical | string | yes | — |
Get the feature-only contract for diagnosing degradation and testing bounded repairs.
No parameter schema on file.
Encrypt a de-identified CSV/JSON payload for a short tenant-private retention window.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | string | yes | — |
| format | string | no | — |
| retention_seconds | integer | no | — |
Encrypt one of up to 64 private feature shards for a large campaign; retain for at least 4,200 seconds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | string | yes | — |
| format | string | no | — |
| retention_seconds | integer | no | — |
Encrypt one complete de-identified repair matrix of up to 100 MB and 1,000 diagnostic features.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | string | yes | — |
| format | string | no | — |
| retention_seconds | integer | no | — |
Validate a tenant-private upload and its baseline evidence/row identity without spending a credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| upload_id | string | yes | — |
| vertical | string | yes | — |
| contract | yes | — |
Validate a tenant-private feature-repair matrix without spending a credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| upload_id | string | yes | — |
| contract | yes | — |
Create a contract-bound quote for one audit credit; baseline mode and evidence cannot be substituted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| upload_id | string | yes | — |
| vertical | string | yes | — |
| contract | yes | — | |
| idempotency_key | string | yes | — |
Preflight and quote label-based feature repair; large jobs return a measured ETA and credit requirement.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| upload_id | string | yes | — |
| contract | yes | — | |
| idempotency_key | string | yes | — |
Preflight all private feature shards, time a pilot, and quote credits and ETA for up to 1,000 candidates in one corrected search family.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vertical | string | yes | — |
| shards | array | yes | — |
| idempotency_key | string | yes | — |
Read beta or paid audit-credit availability and usage.
No parameter schema on file.
Redeem one operator-issued invite for free beta audit credits before January 1, 2027.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| invite_code | string | yes | — |
Request operator-reviewed beta access without purchasing or granting credits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lane | string | yes | — |
| use_case | string | yes | — |
| idempotency_key | string | yes | — |
Read the authenticated tenant's beta-access request status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | string | yes | — |
Accept a quote and atomically reserve its disclosed audit credits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quote_id | string | yes | — |
| idempotency_key | string | yes | — |
Record whether a completed audit changed a decision or was confirmed prospectively.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
| kind | string | yes | — |
| value | string | yes | — |
Read the state of an audit owned by the authenticated tenant.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
Read a completed tenant-private result and signed output manifest.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
Read a tenant-private report fingerprint retained after report expiry or deletion. Older reports may have no record. This does not retrieve report contents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
| sha256 | string | yes | — |
| representation | string | no | — |
Delete retained inputs and results for an audit owned by this tenant.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
Delete a tenant-private upload that is no longer needed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| upload_id | string | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ML Referee or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.1.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest88c0340b54e1e6ecb77160329dca0b789ecb5a24a49555cc7370ad5ce54fffd0
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| describe_referee | no tags | |
| list_verticals | no tags | |
| get_referee_readiness | no tags | |
| get_referee_usage | no tags | |
| get_input_schema | no tags | |
| get_repair_schema | no tags | |
| upload_private_dataset | state-write | state-write: declares readOnlyHint: false |
| upload_campaign_shard | state-write | state-write: declares readOnlyHint: false |
| upload_repair_matrix | state-write | state-write: declares readOnlyHint: false |
| preflight_dataset | state-write | state-write: declares readOnlyHint: false |
| preflight_repair | state-write | state-write: declares readOnlyHint: false |
| quote_audit | state-write | state-write: declares readOnlyHint: false |
| quote_repair | state-write | state-write: declares readOnlyHint: false |
| quote_campaign | state-write | state-write: declares readOnlyHint: false |
| get_credits | state-write | state-write: declares readOnlyHint: false |
| redeem_beta_invite | state-write | state-write: declares readOnlyHint: false |
| request_beta_access | state-write | state-write: declares readOnlyHint: false |
| get_beta_request_status | no tags | |
| submit_audit | state-write | state-write: declares readOnlyHint: false |
| record_audit_followup | state-write | state-write: declares readOnlyHint: false |
| get_audit_status | no tags | |
| get_audit_result | no tags | |
| get_audit_receipt | no tags | |
| verify_audit_report | no tags | |
| delete_audit | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| delete_upload | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest88c0340b54e1e6ec
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish ML Referee can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.