Skills/PyPI/sanctions-mcp

sanctions-mcp@0.4.0

VERIFIED· not started

Publisher claims: "OFAC sanctions screen, KYA, and transaction risk for AI agents — MCP + HTTP + CLI. Real OFAC data, no API key. (package: agentmail)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher kindrat86 · publishing for 141 daysInstalls 55Last detonated 1 h ago
$claude mcp add sanctions-mcp -- uvx sanctions-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
AGENTMAIL_API_KEYSAGENTMAIL_REQUIRE_AUTHAGENTMAIL_TWILIO_TOKENConfiguration, not credentials: AGENTMAIL_AUDIT_LOG, AGENTMAIL_COMPLIANCE_PROVIDER, AGENTMAIL_FIVESIM_KEY, AGENTMAIL_FREE_TIER_DAILY, AGENTMAIL_HOME, AGENTMAIL_MOCK_DELAY, AGENTMAIL_MOCK_FROM, AGENTMAIL_MOCK_KYA_FORCE, AGENTMAIL_MOCK_OTP, AGENTMAIL_MOCK_RISK_FORCE, AGENTMAIL_MOCK_SANCTIONED, AGENTMAIL_RATE_LIMIT, AGENTMAIL_SMS_PROVIDER, AGENTMAIL_TWILIO_NUMBER, AGENTMAIL_TWILIO_SID
Where it talks to
no vendor host named in the codeAlso mail.tm, 5sim.net, treasury.gov, twilio.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names mail.tm, 5sim.net, treasury.gov, twilio.com as well as its own vendor. The guard injects AGENTMAIL_API_KEYS, AGENTMAIL_REQUIRE_AUTH, AGENTMAIL_TWILIO_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sanctions-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-16 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actioncore.py:184 · File type combined with upload action — agent may exfiltrate local data files# Provider holds its own dispute state; compliance.json persists disputes only.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actioncore.py:239 · File type combined with upload action — agent may exfiltrate local data files# Persist to compliance.json so disputes survive restartsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈70 tok
1 file · 29 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for sanctions-mcp@0.4.0 as of 40 min ago. This is the package itself, not its dependencies.