Robin Saige we check the tools AI agents call

My everything app!

live.alpic.staging.everything-app-ce82911c/everything-app

Still WiP

— the operator's own registry description reported

Publisher live.alpic.staging.everything-app-ce82911c · first seen 2026-08-12 · endpoint https://everything-app-ce82911c.staging.alpic.live

allow
verdict
thin-solo
cluster
ok_tools
answers
1
tools served

Dependency rating derived

allow — thin-solo — safe to depend on

Cluster thin-solo · distinctiveness 0.401 (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?
tools1
vs populationlow
capabilities2
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryyes
drift events0
answers trueno primary

🔏 Signed receipt rr_7c2dc4b3308d9f6822432d20 · 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

show-everything

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 & specific1/1
has a description1/1
description is substantive0/10/1
parameters are typed1/1
parameters are described1/1

1 of 1 tools graded · 1 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
0.0.1
server version alpic-openai-app

Capabilities: 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
2026-08-14T20:00:29Zok_tools2001362025-06-18
2026-08-12T05:35:44Zok_tools2006442025-06-18

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/live.alpic.staging.everything-app-ce82911c/everything-app.svg)](https://robinsaige.com/s/live.alpic.staging.everything-app-ce82911c/everything-app)

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