Robin Saige we check the tools AI agents call

demo.st

st.demo/demost

Reserve a subdomain, upload .zip via MCP, get a link. Optional document API at api.demo.st.

— the operator's own registry description reported

Publisher st.demo · first seen 2026-08-12 · endpoint https://demo.st/mcp

allow
verdict
mid-slow-solo
cluster
ok_tools
answers
13
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 13 tools legible (band A) ●, no confirmed drift in 2 probes ●; not yet checked: truth (0 runs)

Cluster mid-slow-solo · distinctiveness 0.307 (typical). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency580 ms
vs populationslow
protocolcurrent
authopen
Can it be used? Q4 · observed
tools13
vs populationmid
capabilities1
harnessA
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_208791f0dc904d1a34bf4591 · 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?action ● evidence ↓
Q3Can it be checked?V n/a for this kind ◐evidence ↓
Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?mid-slow-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 (1 events)
datetypewhat changed
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
action9changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public3serves public factstruth-checkable against a public source — the V-ladder applies in full
unclassified1not classifiable from its textTier-1 only until its tools describe themselves

Tools last seen observed

check_subdomain_availability clear_site create_collection delete_collection delete_record get_site_api_key list_collections list_records release_subdomain reserve_subdomain rotate_site_api_key upload_site upsert_record

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 & specific13/13
has a description13/13
description is substantive12/1312/13
parameters are typed13/13
parameters are described13/13

13 of 13 tools graded · 13 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
1.0.0
server version demo-st

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
2026-08-14T20:00:45Zok_tools2005802025-06-18
2026-08-12T05:35:58Zok_tools2006792025-06-18

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/st.demo/demost.svg)](https://robinsaige.com/s/st.demo/demost)

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