Robin Saige we check the tools AI agents call

blindoracle

io.github.craigmbrown/blindoracle

Trust layer for the x402 agent economy: 40 pay-per-call SKUs, USDC on Base, verifiable proofs.

— the operator's own registry description reported

Publisher io.github.craigmbrown · first seen 2026-08-12 · endpoint https://api.craigmbrown.com/v2/

allow
verdict
rich-solo
cluster
ok_tools
answers
40
tools served

Dependency rating derived

allow
allow — alive & usable · kind unknown · V n/a
allow — because answers ●, 40 tools legible (band A) ●, no confirmed drift in 7 probes ●; not yet checked: truth (0 runs)

Cluster rich-solo · distinctiveness 0.451 (moderate). Every figure is a percentile or class within the 19,148-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency107 ms
vs populationtypical
protocolleading
authopen
Can it be used? Q4 · observed
tools40
vs populationhigh
capabilities1
harnessA
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_05379197aa76228237e6c613 · 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?alive & usable — 7 probes ●evidence ↓
Q2What is it?kind unknown ● evidence ↓
Q3Can it be checked?V n/a for this kind ◐evidence ↓
Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?rich-solo · 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 (7 shown, 2026-08-12 → 2026-09-13). 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
2026-09-13outcomeok_tools (was auth_required)
2026-08-12outcomefirst probe: auth_required

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 tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
unclassified16not classifiable from its textTier-1 only until its tools describe themselves
retrieval-public11serves public factstruth-checkable against a public source — the V-ladder applies in full
action7changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
generative4creates contentno answer key exists; disclosure + stability checks, never truth verdicts
computational2deterministic transformsself-checkable by re-computation and known-answer tests

Tools last seen observed

agent.prehire-check agent.trust-badge arbitration.dispute-settlement attestation.single-use-seal content.youtube-research crypto.investment-plays crypto.market-analyzer data.business-registry data.sec-edgar-filing data.web-extract deliberation.multi-agent-debate finops.token-spend-audit health_check ops.due-diligence-scan ops.link-integrity oracle.alert-generator oracle.comprehensive-report oracle.cross-chain-prices oracle.historical-analysis oracle.market-arbitrage oracle.price-feed oracle.sentiment-analysis oracle.volatility-monitor prediction.blindoracle procurement.council procurement.trust-layer procurement.vendor-vetting reputation.lookup research.topic-deep-researcher research.topic-news-scanner research.topic-sentiment-analyzer security.audit-attestation security.concordium-card-verify security.enterprise-audit security.injection-resilience security.massat-audit security.massat-conformance security.process-attestation social.verified_introduction translation.zh-en

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility checktools passingok
name is clear & specific40/40
has a description40/40
description is substantive40/40
parameters are typed40/40
parameters are described40/40

40 of 40 tools graded · 40 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

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.

Protocol conformance observed

2026-07-28
protocol version
session model
2.0.0
server version BlindOracle

Capabilities: tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-13; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-09-13T06:16:37Zok_tools2001072026-07-28
2026-09-06T06:15:52Zauth_required401110
2026-08-30T06:15:28Zauth_required401107
2026-08-23T06:13:14Zauth_required40198
2026-08-16T06:13:01Zauth_required401154
2026-08-14T19:59:27Zauth_required401112
2026-08-12T05:34:40Zauth_required40188

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.craigmbrown/blindoracle.svg)](https://robinsaige.com/s/io.github.craigmbrown/blindoracle)

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

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →