ZBS Index What actually exists in applied AI, with the source next to it

mcp server

sanctions-screening

Sanctions screening, KYB, identifier validation, jurisdiction risk & secret scanning for AI agents

Description as published by the maintainer. Source

  • version 1.1.0
  • active

active — Most recent push to the repository was 2026-07-17.

What this server can do

13 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

check_jurisdiction(api_key, country)
Classify a country's AML risk against the FATF black/grey lists AND the EU high-risk-third-countries list. Accepts an ISO 3166-1 alpha-2 code or country name. Dated 2026-02-13. Costs $0.005 per call. Required: country.
create_api_key(note)
Create a Watchtower API key with free trial credit. Store the key; screening tools require it.
create_watch(days, name, api_key, threshold, webhook_url)
Monitor a name against all sanctions + US export-control lists. When the daily list refresh changes that name's match set, we POST a "watch_changed" event to your webhook. $0.01/day, prepaid, debited from your API key credit. Max 90 days. Required: name, webhook_url.
get_screening_info
Free: sanctions list versions, source hashes, freshness, entry counts, and the full per-tool price menu.
kyb_check(lei, name, api_key)
Know-Your-Business in one call: resolve a company (by name or LEI) to its GLEIF legal identity AND screen it against sanctions + exclusion lists. Costs $0.02 per call.
list_watches(api_key)
List your active watches (free). Required: api_key.
resolve_lei(lei, api_key)
Resolve a Legal Entity Identifier (LEI) to its official GLEIF record: legal name, status, jurisdiction, country, registration status. The LEI is checksum-validated first. Costs $0.01 per call. Required: lei.
scan_text(text, api_key)
Detect & redact PII and secrets in text (private_key, jwt, aws_access_key, github_token, stripe_key, slack_token, openai_key, google_api_key, sendgrid_key, npm_token, gitlab_token, twilio_key, slack_webhook, azure_storage_key, basic_auth_url, email, ssn, ipv4, eth_address, iban, credit_card, phone). Deterministic; returns findings (masked), counts, and a redacted copy. Use before logging/forwarding untrusted or agent-generated text. Costs $0.005 per call. Required: text.
screen_crypto_address(address, api_key)
Check whether a crypto address (BTC/ETH/others) appears on OFAC's sanctioned digital-currency address list. Exact match. Costs $0.01 per call. Required: address.
screen_name(dob, name, types, api_key, threshold, nationality)
Screen a person/company/vessel name against OFAC (SDN + Consolidated), UN, EU, UK, Canada, Australia, France, Switzerland, US export-control (BIS/State), and US SAM procurement/benefit exclusions. Deterministic, typo-tolerant fuzzy matching. Costs $0.02 per call, debited from your API key credit. Required: name.
screen_names_batch(names, api_key, threshold)
Screen up to 500 names in one call against OFAC SDN, OFAC Consolidated, UN, EU, and UK OFSI sanctions lists. Costs $0.015 per name (25% below single-call price), debited from your API key credit. Required: names.
search_lei_by_name(name, limit, api_key)
Find Legal Entity Identifiers by company legal name via GLEIF — returns candidate records (lei, legal_name, status, jurisdiction, country). Costs $0.01 per call. Required: name.
validate_identifier(type, value, api_key)
Deterministically validate & normalize an identifier by its checksum/format: iban, lei, isin, bic, card, vat, eth, email, domain, phone, uuid, btc, cusip, sedol, imei. Type is auto-detected if omitted. Costs $0.005 per call. Required: value.

Last successful function declaration observed on . Source: https://watchtower-api.com/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://watchtower-api.com/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 0 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-07-17 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 0 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 1.1.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-17 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-07-17 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub
mcp tools declared 13 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe watchtower-api.com
mcp endpoint status ok The server listed 13 functions when asked. as of probe watchtower-api.com

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Mazeh18/watchtower-mcp on GitHub — GitHub, observed , trust tier 3.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.
  3. Tools declared by the MCP server at https://watchtower-api.com/mcp — watchtower-api.com, observed , trust tier 1.