Robin Saige we check the tools AI agents call

Affine.Earth Math Court

earth.affine/math-court

No-float UUM-8D Math Court. Integer courts and certified MCP. Floats refused.

— the operator's own registry description reported

Publisher earth.affine · first seen 2026-08-24 · endpoint https://affine.earth/language-invariant/mcp

allow
verdict
stale-rich-fast-solo
cluster
ok_tools
answers
49
tools served

Dependency rating derived

allow
allow — alive & usable · kind unknown · V n/a
allow — because answers ●, 49 tools legible (band A) ●, no confirmed drift in 2 probes ●; not yet checked: truth (4 attempts unverifiable, 0 disagreements)

Cluster stale-rich-fast-solo · distinctiveness 0.666 (unusual). Every figure is a percentile or class within the 15,472-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency21 ms
vs populationfast
protocolstale
authopen
Can it be used? Q4 · observed
tools49
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_61d47ec926fe97b4a572b47b · 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 — 2 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?stale-rich-fast-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 (2 shown, 2026-08-30 → 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 (2 events)
datetypewhat changed
2026-09-06inventorytools 48 → 49
2026-08-30outcomefirst 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
unclassified16not classifiable from its textTier-1 only until its tools describe themselves
action15changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public10serves public factstruth-checkable against a public source — the V-ladder applies in full
computational5deterministic transformsself-checkable by re-computation and known-answer tests
generative2creates contentno answer key exists; disclosure + stability checks, never truth verdicts
orchestration1routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)

Tools last seen observed

atc.assert_4d_deconfliction code_ir_equiv corpus_bonds corpus_capability_map corpus_coverage critique_frame execute_2local_hamiltonian execute_artifact_crucible execute_exact_permanent execute_transition expose feeds_catalog game_frame_meta ide_rebuild_mesh lattice_op math_court membrane_health noaa_goes_r_weather project_affine_key project_shor_twin route_spin_glass_manifold twin.robotics.evaluate_exact_ik umc_direct umc_resume umc_status verify_amplitude_amplification verify_amplitude_estimation verify_bell_measurement verify_bernstein_vazirani verify_deutsch_jozsa verify_grover verify_hhl verify_jordan_bond verify_n_representability verify_period verify_phase_kickback verify_presented_pair verify_qaoa_energy verify_qft_phases verify_qpe_phase verify_quantum_counting verify_quantum_walk verify_shor_witness verify_simon verify_superdense verify_teleport verify_topological_word verify_vqe_energy weather.convective_containment

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 & specific49/49
has a description49/49
description is substantive49/49
parameters are typed49/49
parameters are described30/4930/49

49 of 49 tools graded · 49 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 — 4 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
OFAC SDN screening (vs the official list)ISLAMIC REVOLUTIONARY GUARD CORPSunverifiableofac-sdn
OFAC SDN screening (vs the official list)MAERSK LINEunverifiableofac-sdn
tariff-duty0901.21.00unverifiableus-hts
tariff-duty6109.10.00unverifiableus-hts

Protocol conformance observed

2024-11-05
protocol version
session model
1.0.0
server version gaiaftcl-edge-membrane

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
2026-09-06T06:13:25Zok_tools200212024-11-05
2026-08-30T06:13:05Zok_tools2003762024-11-05

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/earth.affine/math-court.svg)](https://robinsaige.com/s/earth.affine/math-court)

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 →