Robin Saige we check the tools AI agents call

FreightUtils MCP Server

io.github.SoapyRED/freightutils

Neutral freight reference + validation layer for AI agents: ADR, HS, UN/LOCODE, freight math

— the operator's own registry description reported

Publisher io.github.SoapyRED · first seen 2026-08-12 · endpoint https://www.freightutils.com/api/mcp

allow
verdict
mid-solo
cluster
ok_tools
answers
24
tools served

Dependency rating derived

allow — mid-solo — safe to depend on

Cluster mid-solo · distinctiveness 0.477 (moderate). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency315 ms
vs populationtypical
protocolcurrent
authopen
Use — can it use it?
tools24
vs populationmid
capabilities3
harnessA
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true23/23 agree

🔏 Signed receipt rr_9cced61daf8056e778d3ebd6 · 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.

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. This server's 24 tools, classified, with what checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
computational18deterministic transformsself-checkable by re-computation and known-answer tests
retrieval-public4serves public factstruth-checkable against a public source — the V-ladder applies in full
generative2creates contentno answer key exists; disclosure + stability checks, never truth verdicts

Tools last seen

adr_exemption_calculator adr_lookup adr_lq_eq_check airline_lookup airport_lookup cbm_calculator chargeable_weight_calculator consignment_calculator container_lookup emissions_calculator get_subscribe_link hs_code_lookup ics2_check incoterms_lookup ldm_calculator nearest_airport pallet_fitting_calculator shipment_summary uk_duty_calculator uld_lookup unit_converter unlocode_lookup validate vehicle_lookup

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 & specific24/24✓
has a description24/24✓
description is substantive24/24✓
parameters are typed24/24✓
parameters are described24/24✓

24 of 24 tools graded · 24 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

23/23 answers agree with the published primary source.

claim classkeyverdictprimary source
ISO 6346 container20ft-standardagreesiso-6346
ISO 6346 container40ft-high-cubeagreesiso-6346
ISO 6346 container40ft-standardagreesiso-6346
HS 2022 code090111agreeswco-hs-2022
HS 2022 code100630agreeswco-hs-2022
HS 2022 code220300agreeswco-hs-2022
HS 2022 code610910agreeswco-hs-2022
HS 2022 code850760agreeswco-hs-2022
Incoterms 2020CFRagreesicc-incoterms-2020
Incoterms 2020CIFagreesicc-incoterms-2020
Incoterms 2020CIPagreesicc-incoterms-2020
Incoterms 2020CPTagreesicc-incoterms-2020
Incoterms 2020DAPagreesicc-incoterms-2020
Incoterms 2020DDPagreesicc-incoterms-2020
Incoterms 2020DPUagreesicc-incoterms-2020
Incoterms 2020EXWagreesicc-incoterms-2020
Incoterms 2020FASagreesicc-incoterms-2020
Incoterms 2020FCAagreesicc-incoterms-2020
Incoterms 2020FOBagreesicc-incoterms-2020
UN/LOCODECNSHAagreesunece-unlocode
UN/LOCODENLRTMagreesunece-unlocode
UN/LOCODESGSINagreesunece-unlocode
UN/LOCODEUSLAXagreesunece-unlocode

Protocol conformance observed

2025-06-18
protocol version
—
session model
2.15.0
server version freightutils-mcp

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 (7 shown, 2026-08-12 → 2026-08-15). 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
2026-08-15T05:10:09Zok_tools2003702025-06-18
2026-08-14T19:59:16Zok_tools2003152025-06-18
2026-08-14T05:10:09Zok_tools2005842025-06-18
2026-08-13T05:10:09Zok_tools2003572025-06-18
2026-08-12T19:49:40Zok_tools2003442025-06-18
2026-08-12T17:50:21Zok_tools2009142025-06-18
2026-08-12T05:34:29Zok_tools2003222025-06-18

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.SoapyRED/freightutils.svg)](https://robinsaige.com/s/io.github.SoapyRED/freightutils)

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