Robin Saige we check the tools AI agents call

Cofferline

com.cofferline/treasury

Treasury and risk controls for agent wallets: policies, quotes, prediction-market orders.

— the operator's own registry description reported

Publisher com.cofferline · first seen 2026-08-21 · endpoint https://mcp.cofferline.com

allow
verdict
rich-solo
cluster
ok_tools
answers
47
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 47 tools legible (band A) ●, no confirmed drift in 3 probes ●; not yet checked: truth (1 attempts unverifiable, 0 disagreements)

Cluster rich-solo · distinctiveness 0.466 (moderate). Every figure is a percentile or class within the 15,472-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency107 ms
vs populationtypical
protocolcurrent
authopen
Can it be used? Q4 · observed
tools47
vs populationhigh
capabilities1
harnessA
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_f8e3ac32803adfd0623b8878 · 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 — 3 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?rich-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 (3 shown, 2026-08-23 → 2026-09-06). 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
2026-08-23outcomefirst 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
action18changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
unclassified15not classifiable from its textTier-1 only until its tools describe themselves
retrieval-public13serves public factstruth-checkable against a public source — the V-ladder applies in full
predictive1claims about the futurescoreable only in retrospect — the archive scores yesterday's predictions against today's outcome

Tools last seen observed

cancel_all_pm_orders cancel_intent cancel_pm_order check_pm_order check_spend complete_siwe_login confirm_delegation create_intent create_pm_order export_account get_auto_topup get_balance get_benchmarks get_delegation get_intent get_me get_pm_onboarding get_pm_signer_rotation get_policy get_quotes get_statement list_delegations list_feedback list_intents list_pm_credentials list_pm_orders list_tokens offboard_account panic poll_events prepare_delegation prepare_pm_order put_policy remove_auto_topup renew_delegation resolve_pm_funder revoke_delegation revoke_pm_credential screen_address set_auto_topup start_siwe_login store_pm_credential submit_feedback submit_pm_order sync_pm_fills topup_balance wrap_pm_usdc

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 & specific47/47
has a description47/47
description is substantive46/4746/47
parameters are typed47/47
parameters are described44/4744/47

47 of 47 tools graded · 47 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 yet confirmed — 1 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
OFAC SDN screening (vs the official list)unmappedunverifiableofac-sdn

Protocol conformance observed

2025-06-18
protocol version
session model
377059f60392709c6831bb3f737b2a1bfc79e266
server version Cofferline MCP

Capabilities: tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-06; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-09-06T06:12:14Zok_tools2001072025-06-18
2026-08-30T06:11:59Zok_tools2001072025-06-18
2026-08-23T06:11:42Zok_tools200822025-06-18

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/com.cofferline/treasury.svg)](https://robinsaige.com/s/com.cofferline/treasury)

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

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →