Robin Saige we check the tools AI agents call

Compliance & Sanções

io.github.mcp-dir/compliance-mcp

Due diligence & KYC: PEP, national and international sanctions (OFAC, UN, EU, UK, FBI, INTERPOL, FIN

— the operator's own registry description reported

Publisher io.github.mcp-dir · first seen 2026-08-22 · endpoint https://api.mcp.ai/p_compliance

allow
verdict
gateway
cluster
ok_tools
answers
37
tools served

Dependency rating derived

allow
allow — gateway · retrieval-public ● · V3 has answer key ◐
allow — because answers ●, 37 tools legible (band B) ●, no confirmed drift in 3 probes ●; not yet checked: truth (2 attempts unverifiable, 0 disagreements)

Cluster gateway · distinctiveness 0.512 (moderate). Every figure is a percentile or class within the 15,472-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency75 ms
vs populationfast
protocolcurrent
authopen
Can it be used? Q4 · observed
tools37
vs populationhigh
capabilities1
harnessB
Did it hold when checked? Q3–Q4 · derived
identityfarm_member
servers on its host1115
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_8ab7a4d3d07ae2e061363cea · 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?gateway — 3 probes ●evidence ↓
Q2What is it?retrieval-public ● evidence ↓
Q3Can it be checked?V3 has answer key ◐evidence ↓
Q4Did it hold?harness B · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?gateway · 1115 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
retrieval-public35serves public factstruth-checkable against a public source — the V-ladder applies in full
action2changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions

Tools last seen observed

authenticate compliance_antecedentes_civil compliance_antecedentes_pf compliance_antt compliance_bacen_inabilitados compliance_bacen_proibidos compliance_cadin compliance_carf compliance_ceaf compliance_ceis compliance_cepim compliance_cgu compliance_cnd_municipal compliance_cnep compliance_confea_crea compliance_cvm compliance_cvm_sancionadores compliance_fbi compliance_fincen compliance_ibama_debitos compliance_improbidade compliance_interpol compliance_leniencia compliance_mandados_prisao compliance_ofac compliance_onu compliance_pep compliance_pep_parentescos compliance_pix compliance_trabalho_forcado compliance_ue compliance_uk connect marketplace report_bug show_version toolkit_info

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 & specific37/37
has a description37/37
description is substantive33/3733/37
parameters are typed37/37
parameters are described3/373/37

37 of 37 tools graded · 37 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 — 2 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)ISLAMIC REVOLUTIONARY GUARD CORPSunverifiableofac-sdn
OFAC SDN screening (vs the official list)MAERSK LINEunverifiableofac-sdn

Protocol conformance observed

2025-06-18
protocol version
session model
0.9.342
server version mcp-ai

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
2026-09-06T06:16:24Zok_tools200752025-06-18
2026-08-30T06:15:59Zok_tools2001782025-06-18
2026-08-23T06:13:37Zok_tools2002942025-06-18

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.mcp-dir/compliance-mcp.svg)](https://robinsaige.com/s/io.github.mcp-dir/compliance-mcp)

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 →