Robin Saige we check the tools AI agents call

values firewall

dk.humanified/values-firewall

EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.

— the operator's own registry description reported

Publisher dk.humanified · first seen 2026-08-12 · endpoint https://vf.humanified.dk/mcp

allow
verdict
thin-slow-shared
cluster
ok_tools
answers
3
tools served

Dependency rating derived

allow — thin-slow-shared — safe to depend on

Cluster thin-slow-shared · distinctiveness 0.709 (unusual). 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
latency377 ms
vs populationslow
protocolcurrent
authopen
Use — can it use it?
tools3
vs populationlow
capabilities6
harnessA
Trust — can it rely on it?
identityshared
servers on its host1
servers on its domain3
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_8af8c6960e89678d478b39bb · 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

check_action check_action_deterministic list_charter

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 & specific3/3
has a description3/3
description is substantive3/3
parameters are typed3/3
parameters are described1/31/3

3 of 3 tools graded · 3 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
3.4.5
server version values-firewall

Capabilities: experimental extensions logging 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
2026-08-14T19:58:46Zok_tools2003772025-06-18
2026-08-12T05:34:00Zok_tools2006312025-06-18

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/dk.humanified/values-firewall.svg)](https://robinsaige.com/s/dk.humanified/values-firewall)

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