Robin Saige we check the tools AI agents call

Andreax x402 Services

io.github.moralito311-andr/andreax

54 pay-per-call AI services over x402 (USDC on Base): compression, OCR, FX, inference.

— the operator's own registry description reported

Publisher io.github.moralito311-andr · first seen 2026-08-17 · endpoint https://pagos.andreax.dev/mcp

allow
verdict
rich-slow-solo
cluster
ok_tools
answers
160
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 160 tools legible (band A) ●, no confirmed drift in 3 probes ●; not yet checked: truth (1 attempts unverifiable, 0 disagreements)

Cluster rich-slow-solo · distinctiveness 0.673 (unusual). Every figure is a percentile or class within the 15,472-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency894 ms
vs populationslow
protocolcurrent
authopen
Can it be used? Q4 · observed
tools160
vs populationhigh
capabilities1
harnessA
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_172f3eae8808123762b2fd2f · 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 — 3 probes ●evidence ↓
Q2What is it?action ● 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-slow-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 (3 shown, 2026-08-23 → 2026-09-06). 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 (3 events)
datetypewhat changed
2026-09-06inventorytools 64 → 160
2026-08-30inventorytools 54 → 64
2026-08-23outcomefirst probe: ok_tools

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
action160changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions

Tools last seen observed

ab-test-designer agent-blueprint agtech-market ai-agents-market-2026 ai-compliance-global ai-inference annual-report-pipeline audio-to-text autonomous-workflow base-ecosystem-report blog-post-pipeline blog-repurpose brand-strategy business-plan classify-topic code-explain code-gen code-review code-review-security combo-compet-market-email-70c7ad combo-discre-agtech-3c62b9 combo-gtm-email-crypto-2e0abb competitive-analysis competitor-monitoring competitor-scan compliance-audit compress comprimir contar-tokens content-pipeline contract-draft count-tokens cron crypto-backtest crypto-payments-2026 crypto-price custom-workflow-design customer-onboarding-sequence customer-reply deep-research-report destilar destilar-batch destilar-multi-language destilar-structured-json destilar-tables detect-language developer-tools-report discrepancy-detector doc-extract due-diligence ecommerce-pricing edutech-curriculum email-campaign-pipeline email-polish embeddings enterprise-ai-adoption enterprise-compliance entities explain extract-json fact-check fact-check-quick faq fast-translate fintech-compliance fx global-saas-pricing grant-proposal gtm-strategy headlines healthcare-compliance image-describe inference interpret interpretar investor-deck-copy investor-pitch invoice-batch json-fix keywords language-detect latam-fintech-report lead-enrich legal-latam legal-review logistics-optimization market-data market-intelligence market-reality-check market-research-report market-sector-report mcp-servers-landscape meeting-brief meeting-minutes moderate multi-agent-debate ocr ocr-batch ocr-business-cards ocr-demo ocr-handwriting ocr-invoices ocr-multi-language ocr-receipts ocr-receipts-biz ocr-receipts-biz2 ocr-structured-json ocr-tables osint-signal podcast-pipeline portfolio-analysis predictive-analytics product-listing proofread proposal-draft quarterly-review quick-summary read-pdf read-url real-estate-report regex reply report research resumen-traduccion-demo retailer-intel rewrite-formal risk-analysis rwa-report saas-churn-analysis sales-email screen-aware-assist semantic-search sentiment seo-article smart-document social-calendar social-media-calendar-30 strategy-plan summarize technical-audit text-to-sql topic-classify trading-signal traducir traductor-juridico transcribe translate-doc translate-en translate-to video-creator vision vision-batch vision-multi-language vision-structured-json vision-tables voice-clone-tts wallet-balance x402-payments-landscape youtube-script-pipeline

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 & specific159/160159/160
has a description160/160
description is substantive160/160
parameters are typed160/160
parameters are described160/160

160 of 160 tools graded · 160 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 yet confirmed — 1 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
fx-ratesunmappedunverifiableecb-fx

Protocol conformance observed

2025-06-18
protocol version
session model
1.1.0
server version Andreax x402 Services

Capabilities: tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-06; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-09-06T06:16:41Zok_tools2008942025-06-18
2026-08-30T06:16:29Zok_tools2003362025-06-18
2026-08-23T06:13:58Zok_tools2004912025-06-18

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.moralito311-andr/andreax.svg)](https://robinsaige.com/s/io.github.moralito311-andr/andreax)

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 →