
Sanctions Screening
com.watchtower-apiPublished by watchtower-api.comOfficial publisherv1.1.0Updated Oct 24, 2026
Sanctions screening, KYB, identifier validation, jurisdiction risk & secret scanning for AI agents
Overview
Hosted compliance API that lets an assistant screen names against sanctions lists, run KYB checks, validate identifiers, and scan text for PII and secrets.
- What you can do
- Screen people, companies and vessels against sanctions and exclusion lists, and check crypto addresses against OFAC's list
- Run one-call KYB combining GLEIF legal identity with sanctions screening, and resolve or search LEIs
- Validate and normalize identifiers such as IBAN, LEI, ISIN, BIC, VAT, card numbers and crypto addresses by checksum
- Classify jurisdictions by FATF and EU AML risk, and detect and redact PII and secrets in text
- Create watches that fire a webhook when a name's sanctions matches change, and read list versions, freshness and pricing
- When to use it
- Useful when an assistant has to support onboarding, KYC/KYB or compliance review work: checking a counterparty against official sanctions lists, confirming a legal entity identity, validating payment or entity identifiers, or redacting sensitive data before it is shared.
- Requirements
- Remote streamable-HTTP endpoint; nothing to install. Paid tools take an api_key argument, obtainable through the create_api_key tool with trial credit, or are paid per call via x402 in USDC on Base. Network access to the hosted endpoint is required.
Installation
In SourceWeft
- Open Sanctions Screening in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.watchtower-api%2Fsanctions-screening/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"sanctions-screening": {
"type": "http",
"url": "https://watchtower-api.com/mcp"
}
}
}README
Watchtower — Compliance & Data-Integrity MCP Server for AI Agents
Live hosted MCP endpoint: https://watchtower-api.com/mcp · Docs: https://watchtower-api.com/docs · OpenAPI: https://watchtower-api.com/openapi.json
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.
This repo is the public home for the hosted Watchtower MCP server. There's nothing to install — connect to the remote endpoint below.
Connect
Streamable-HTTP MCP, stateless — no auth handshake. Paid tools take an api_key argument (create one for free with the create_api_key tool, which includes trial credit) or you can pay per call via x402.
Tools
Why Watchtower
- 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.
Also available as REST + x402
Everything above is also a REST API. Pay per call in USDC via x402 with no signup:
Full reference: https://watchtower-api.com/docs · machine-readable: /llms.txt, /openapi.json, /.well-known/x402.json
Informational screening against public sanctions, export-control & exclusion lists; LEI/entity data via GLEIF. Not legal advice.
Source: README.md at commit e4a6c68
Tools
0Version history
1- v1.1.0LatestSep 16, 2026
Score
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.