RU
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Nothing to run from here
Verdict 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.
100/100
trust score
14
tools declared
local
runs on your machine
—
downloads a day
What it does
Score text, files and pages against a rubric with decision models; compare models on your cases.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ustay-coder-verdict-mcp '--' npx -y @verdict-ai/mcp
# 2 — ask your agent for something these tools do
# validate_rubric, create_rubric, list_rubrics and 11 more
Verdict costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
UCAll 1 server
ustay-coder1 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. This one runs on your machine: your client starts Verdict as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user ustay-coder-verdict-mcp '--' npx -y @verdict-ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take TYPESAFE_API_KEY (Key for Jev, the default decision model, when judging runs in this process.), CLOUDFLARE_ACCOUNT_ID (Cloudflare account for Clef and Clef-flash on Workers AI.), CLOUDFLARE_API_TOKEN (Cloudflare token (Workers AI: Read) for Clef and Clef-flash.), OPENAI_API_KEY (Key for OpenAI's Decisions API.), VERDICT_DATA_DIR (Folder to keep rubrics and evaluations in between runs. Without it they are kept in memory.), VERDICT_API_URL (Address of a Verdict API to use instead of judging in this process.), VERDICT_API_KEY (Key for that Verdict API.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
14 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Validate a rubric (JSON object or YAML string) and return it with defaults filled in. Use before evaluate to catch mistakes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rubric | yes | — |
Store a rubric and get back its id for reuse. Criteria need id/name; optional weight, scale, anchors (= rubric levels for decision models), judge ({type: decision|human|benchmark|llm|panel}; default decision/typesafe). Aggregation supports weighted_mean, weighted_sum, mean, median, min, max,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rubric | yes | — |
List stored rubrics.
No parameter schema on file.
Compare decision confidence against human consensus on stored evaluations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rubricId | string | yes | — |
| target | number | no | — |
| buckets | integer | no | — |
Score a subject against a rubric. rubric is a stored rubric id or an inline rubric. Inputs can be text, json, file (path or base64), url (set screenshot: true to let vision judges such as Clef see the page), image (PNG/JPEG/WebP, path or base64), or youtube. Returns the total score, grade,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rubric | yes | — | |
| inputs | array | yes | — |
| name | string | no | Subject name for reports |
| idempotencyKey | string | no | — |
| metadata | object | no | — |
Evaluate several subjects against one rubric and return a ranking (leaderboard).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rubric | yes | — | |
| idempotencyKey | string | no | — |
| subjects | array | yes | — |
Fetch an evaluation by id (status, scores, rationales, pending human tasks).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Submit a human rater's score for a criterion that is waiting on a human. Score is a number on the criterion scale or an ordinal/binary label.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| evaluationId | string | yes | — |
| criterionId | string | yes | — |
| raterId | string | yes | — |
| score | yes | — | |
| rationale | string | no | — |
Recompute the total with a different aggregation (method, formula, weights via gates/grades/passThreshold) without re-running judges. Useful for what-if analysis.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| evaluationId | string | yes | — |
| aggregation | object | yes | — |
| persist | boolean | no | — |
Criteria waiting on human raters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rater | string | no | — |
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- 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 Verdict 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: —
ATrust score 100 / 100
Release 0.3.2 · scanned 12 Nov 2026
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 score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest405bf9b0b94edfefa9f114e5cecd4e770f3a027872397493c73f09cab3913c42
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| check_against_humans | no tags | |
| hub_search | no tags | |
| hub_get | no tags | |
| fork_rubric | no tags | |
| validate_rubric | no tags | |
| create_rubric | no tags | |
| list_rubrics | no tags | |
| calibration_report | no tags | |
| evaluate | no tags | |
| compare | no tags | |
| get_evaluation | untrusted-input | untrusted-input: keyword "fetch" |
| submit_human_score | no tags | |
| reaggregate | no tags | |
| list_human_tasks | no tags |
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 digest405bf9b0b94edfef
Scanned2026-11-12
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.2. Pin a release below and the command asks for exactly that one.
0.3.2
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 Verdict 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.