Sanctions MCP Server

Sanctions MCP server exists for a simple reason — assistants are far more useful when they can act on Sanctions directly instead of describing what you should do. Sanctions screening, KYB, identifier validation, jurisdiction risk & secret scanning for AI agents.

What you get

Watchtower is a deterministic compliance & data-integrity API for AI agents. Point any MCP client at the hosted endpoint and your agent gets tools for sanctions screening, KYB, identifier validation, jurisdiction risk, PII/secret detection, and LEI resolution — pay per call with x402 (USDC on Base, no signup) or a prepaid API key.

• Deterministic & auditable — — same query + same list snapshot ⇒ byte-identical result, stamped with a content-hash and algorithm version, plus point-in-time (as_of) screening for "what did the list say when we onboarded them?"
• Broad, authoritative coverage — — 10 official government lists, ~229,000 parties, refreshed daily
• Built for agents — — pay-per-call via x402 (USDC on Base, no account) or MCP; no minimums, no seats

What the assistant can call

Once Sanctions is connected, these are the calls the assistant has available:

• screen_name — Screen a person/company/vessel against 10 sanctions & exclusion lists (OFAC SDN+Consolidated, UN, EU, UK OFSI, Canada, Australia, France
• kyb_check — One-call KYB: company name → its official GLEIF legal identity and its sanctions/exclusions screening
• screen_crypto_address — Check a crypto address against OFAC's sanctioned-address list
• validate_identifier — Validate/normalize IBAN, LEI, ISIN, BIC, VAT, card (Luhn), Ethereum & Bitcoin addresses, email, and more — by checksum
• check_jurisdiction — FATF (black + grey) and EU high-risk-country AML classification, dated & sourced
• scan_text — Detect & redact PII and secrets (API keys, private keys, tokens, emails, cards, IBANs, SSNs) in text
• create_watch — Monitor a name; webhook fires when its sanctions match set changes
• get_screening_info — List versions, source freshness, entry counts, pricing

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Choosing this one

Plenty of team communication servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Sanctions's toolset — screen_name, kyb_check, screen_crypto_address and 5 more — is a fair guide to whether it matches your workflow. It is maintained by com.watchtower-api; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

• Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the sanctions mcp server does with a few real requests.