Skip to content

Jithox EU Counterparty Sanctions Preflight

by jithox.com · remote · no sign-in to list tools · v0.2.2 · published by com.jithox

Read-only EU sanctions preflight: screen names/IDs against EU list. Evidence, not a verdict.

Changes · 3
CompareRegistry entry

5 tools: 3 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http eu-sanctions-preflight https://sanctions.mcp.jithox.com/mcp --header 'Authorization: <your-authorization>'

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 3Claude Code: ask
  • prepare_screening_receiptBundle the screening checks into one idempotent Ed25519-signed receipt committing to the HASHED inputs, sources, snapshot checksum, retrieval times and decision states — provable e…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Bundle the screening checks into one idempotent Ed25519-signed receipt committing to the HASHED inputs, sources, snapshot checksum, retrieval times and decision states — provable evidence of WHAT was screened and WHEN. Attests the checks, not a clearance or a 'not sanctioned' claim. Screening evidence only; not a legal/compliance determination, not a clearance.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
  • screen_sanctioned_identifierDeterministic EXACT match of an identifier (passport / national id / registration / other) against listed designations' identifiers — no fuzzy matching.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Deterministic EXACT match of an identifier (passport / national id / registration / other) against listed designations' identifiers — no fuzzy matching. 'match' / 'clear' / 'unavailable'. Screening evidence only; not a legal/compliance determination, not a clearance. A 'clear' is not a guarantee of non-designation — snapshot-scoped.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
  • screen_sanctioned_nameScreen a counterparty name against a dated snapshot of the official EU Consolidated Financial Sanctions List.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Screen a counterparty name against a dated snapshot of the official EU Consolidated Financial Sanctions List. Returns ranked CANDIDATE designations with deterministic match scores, or 'clear'/'needs_review'/'possible_match'/'match'; no snapshot → 'unavailable'. Never a false clear on outage or fuzzy input. Screening evidence only; not a legal/compliance determination, not a clearance. A 'clear' is not a guarantee of non-designation — snapshot-scoped. Every result carries source, publication date, checksum and retrieval time.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
Only reads 2Claude Code: allow
  • get_sanctions_listingReturn the full official listing detail (names, programme, legal basis, listing date, identifier types, countries) for a candidate logicalId surfaced by a prior screen, with proven…No findings

    Why it is in this group

    • The name "get_sanctions_listing" says "get": a word for reading.
    Description, as the server wrote it
    Return the full official listing detail (names, programme, legal basis, listing date, identifier types, countries) for a candidate logicalId surfaced by a prior screen, with provenance. 'found' / 'not_found' / 'unavailable'. Screening evidence only; not a legal/compliance determination, not a clearance. Every result carries source, publication date, checksum and retrieval time.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
  • list_sanctions_regimesEnumerate the EU sanctions programmes/regimes present in the snapshot (regulation/legal basis, since date, subject count) — the policy-layer read.No findings

    Why it is in this group

    • The name "list_sanctions_regimes" says "list": a word for reading.
    Description, as the server wrote it
    Enumerate the EU sanctions programmes/regimes present in the snapshot (regulation/legal basis, since date, subject count) — the policy-layer read. 'found' / 'unavailable'. Reference only, not legal advice. Every result carries source, publication date, checksum and retrieval time.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 0.2.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http eu-sanctions-preflight https://sanctions.mcp.jithox.com/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__eu-sanctions-preflight__get_sanctions_listing",
      "mcp__eu-sanctions-preflight__list_sanctions_regimes"
    ],
    "ask": [
      "mcp__eu-sanctions-preflight__screen_sanctioned_name",
      "mcp__eu-sanctions-preflight__screen_sanctioned_identifier",
      "mcp__eu-sanctions-preflight__prepare_screening_receipt"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as eu-sanctions-preflight. Review it before you use it.