Robin Saige we check the tools AI agents call

Qiniso

io.github.qinisolabs/qiniso

Deterministic fact verification for AI agents — checksums & curated data, not guesses.

— the operator's own registry description reported

Publisher io.github.qinisolabs · first seen 2026-08-12 · endpoint https://qiniso.qinisolabs.workers.dev/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
56
tools served

Dependency rating derived

allow — rich-solo — safe to depend on

Cluster rich-solo · distinctiveness 0.385 (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
latency136 ms
vs populationtypical
protocolcurrent
authopen
Use — can it use it?
tools56
vs populationhigh
capabilities1
harnessA
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_d945aa998d1cb9014c0b1ee5 · 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

format_currency is_holiday next_holiday parse_address parse_date tax_rate validate_aadhaar validate_be_nrn validate_bg_egn validate_bsn validate_btc_address validate_card validate_ch_ahv validate_china_ric validate_cnpj validate_codice_fiscale validate_cpf validate_cusip validate_cz_rc validate_de_steuer_id validate_dni validate_domain validate_ee_isikukood validate_email validate_eth_address validate_fodselsnummer validate_fr_nir validate_gln validate_gtin validate_hetu validate_hr_oib validate_iban validate_imei validate_ip validate_isbn validate_isbn10 validate_isin validate_issn validate_lei validate_mx_curp validate_nif_pt validate_orcid validate_personnummer validate_pesel validate_phone validate_ro_cnp validate_routing validate_sa_id validate_sedol validate_sscc validate_tckn validate_tld validate_url validate_uuid validate_vat validate_vin

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 & specific56/56
has a description56/56
description is substantive56/56
parameters are typed56/56
parameters are described56/56

56 of 56 tools graded · 56 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

2025-06-18
protocol version
session model
0.5.0
server version qiniso

Capabilities: 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
2026-08-14T20:00:09Zok_tools2001362025-06-18
2026-08-12T05:35:21Zok_tools2001362025-06-18

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.qinisolabs/qiniso.svg)](https://robinsaige.com/s/io.github.qinisolabs/qiniso)

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