Robin Saige we check the tools AI agents call

aaaa-nexus — Formally Verified AI Safety APIs

io.github.atomadictech/aaaa-nexus

Formally verified AI safety APIs. Pay-per-call via USDC (x402). 75+ endpoints, no signup.

— the operator's own registry description reported

Publisher io.github.atomadictech · first seen 2026-08-12 · endpoint https://aaaa-nexus.atomadictech.workers.dev/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
44
tools served

Dependency rating derived

allow — rich-solo — safe to depend on

Cluster rich-solo · distinctiveness 0.572 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency158 ms
vs populationtypical
protocolleading
authopen
Use — can it use it?
tools44
vs populationhigh
capabilities3
harnessA
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_3d638c04e362ad7ec01c550e · 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.

Tools last seen

aegis_mcp_proxy_execute aegis_router_epistemic_bound agents_plan authorize_action certify_codebase certify_output contract_verify docs_generate entitlement_attest federation_mint forge_audit forge_certify forge_recon forge_tier_infer forge_wire hallucination_oracle identity_verify intent_classify keys_validate lineage_record lint_analyze omega_emit_materialize omega_emit_polyglot omega_intent_nl omega_intent_route rag_augment ratchet_register rng_quantum spending_authorize sys_constants sys_lint_gate sys_trust_gate text_summarize threat_score uep_aha_detect uep_autopoiesis_plan uep_context uep_preflight uep_synthesis_guard uep_trace_certify vanguard_continuous_redteam vanguard_escrow_lock_and_verify vanguard_mev_route_intent vanguard_wallet_govern_session

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 & specific44/44
has a description44/44
description is substantive43/4443/44
parameters are typed44/44
parameters are described44/44

44 of 44 tools graded · 44 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

2025-11-25
protocol version
session model
0.5.1
server version aaaa-nexus

Capabilities: prompts resources tools

Drift

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

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 (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:59:23Zok_tools2001582025-11-25
2026-08-12T05:34:36Zok_tools2001122025-11-25

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.atomadictech/aaaa-nexus.svg)](https://robinsaige.com/s/io.github.atomadictech/aaaa-nexus)

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