Robin Saige we check the tools AI agents call

concordance

com.narrowhighway/concordance

Deterministic claim verification with receipts across ~60 domains. No model in the loop.

— the operator's own registry description reported

Publisher com.narrowhighway · first seen 2026-08-12 · endpoint https://narrowhighway.com/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
88
tools served

Dependency rating derived

allow
allow — alive & usable · kind unknown · V n/a
allow — because answers ●, 88 tools legible (band B) ●, no confirmed drift in 2 probes ●; not yet checked: truth (3 attempts unverifiable, 0 disagreements)

Cluster rich-solo · distinctiveness 0.417 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency260 ms
vs populationtypical
protocolcurrent
authopen
Can it be used? Q4 · observed
tools88
vs populationhigh
capabilities1
harnessB
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_3cf3c7dd8e636eee103a4ddd · 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 B · 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 (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
2026-08-14inventorytools 86 → 88
2026-08-12outcomefirst 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
unclassified35not classifiable from its textTier-1 only until its tools describe themselves
retrieval-public23serves public factstruth-checkable against a public source — the V-ladder applies in full
action20changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
generative6creates contentno answer key exists; disclosure + stability checks, never truth verdicts
computational4deterministic transformsself-checkable by re-computation and known-answer tests

Tools last seen observed

ask attest_record audit backmatter badges_issue badges_verify bible_places calendar_create candidate_commit candidate_get candidate_narrow canon capabilities card_connections card_get cards_browse cards_stats character_get characters_browse coach_guidance coach_mastery coach_next coach_overview coach_recommend coach_subjects coach_unit commentary commons_read consent_check cross_references curate curate_queue curate_signable daily_card deck_open decks grid_axis grid_dimension group_contribute group_create group_get group_join groups_list harmony identity_create identity_fingerprint identity_verify library_health locate mesh_door mesh_inbox mesh_leave_on_door mesh_map mesh_post mesh_signable moderation_signable narratives now original_words pronounce prophecy_traces read_passage redact report resolve seal_fetch search seeds self_attest shelf_drop shelf_read shelf_signable steward_budget steward_cost_destroyed study_create study_export study_find study_import teachings timeline tsk_cross_references verify want_offer want_open wants_list witnesses word_occurrences word_study

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 B — usable, with rough edges.

legibility checktools passingok
name is clear & specific88/88
has a description88/88
description is substantive88/88
parameters are typed88/88
parameters are described16/8816/88

88 of 88 tools graded · 88 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 — 3 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
tariff-duty0901.21.00unverifiableus-hts
tariff-duty6109.10.00unverifiableus-hts
tariff-duty8471.30.01unverifiableus-hts

Protocol conformance observed

2025-06-18
protocol version
session model
2.0.0a0
server version narrow-highway

Capabilities: tools

Drift observed

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

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:58:20Zok_tools2002602025-06-18
2026-08-12T05:33:35Zok_tools2003292025-06-18

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/com.narrowhighway/concordance.svg)](https://robinsaige.com/s/com.narrowhighway/concordance)

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