Robin Saige we check the tools AI agents call

WebUAT-Forensic

io.github.Evozim/webapp-uat

Forensic accessibility and UI/UX front-end audit tool for web apps.

— the operator's own registry description reported

Publisher io.github.Evozim · first seen 2026-08-12 · endpoint https://webapp-uat-mcp.vercel.app/api/mcp

warn
verdict
paywalled
cluster
payment_required
answers
tools served

Dependency rating derived

warn
warn — behind a login · kind unknown · V n/a
warn — because behind a login ●, no confirmed drift in 2 probes ●; not yet checked: harness, truth (0 runs)

Cluster paywalled · distinctiveness —. Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answerspaywalled
latency75 ms
protocolunknown
authpaywalled
Can it be used? Q4 · observed
capabilities0
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_08ffbb044925f3ef5eb31b7f · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Q1Does it answer?behind a login — 2 probes ●evidence ↓
Q2What is it?kind unknown ○ evidence ↓
Q3Can it be checked?V n/a for this kind ◐evidence ↓
Q4Did it hold?truth not yet run · no drift ●evidence ↓
Q5What company does it keep?paywalled · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (2 events)
datetypewhat changed
2026-08-14outcomepayment_required (was http_error)
2026-08-12outcomefirst probe: http_error

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from the operator's own registry description — REPORTED, not observed (tools were not visible to the probe). What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
unclassified1not classifiable from its textTier-1 only until its tools describe themselves

Tools last seen observed

no tool inventory served

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Drift observed

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:59:01Zpayment_required40275
2026-08-12T05:34:15Zhttp_error40295

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.Evozim/webapp-uat.svg)](https://robinsaige.com/s/io.github.Evozim/webapp-uat)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview