Sanctionwise MCP server
Verified UK sanctions screening for AI agents — official FCDO UK Sanctions List, not guesses.
0 stars53 downloads/wk
Reviews
Write oneNobody has reviewed Sanctionwise yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Sanctionwise tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
get_sanctions_entryUSE THIS to fetch the full official UK Sanctions List entry for a Unique ID (e.g. one returned by screen_name) — all names/aliases, regime, designation date, sanctions imposed, nationality/DOB, and the UK statement of reasons.
screen_nameUSE THIS to screen a person, company or vessel name against the UK Sanctions List before onboarding, paying, or transacting with them — never decide from memory whether someone is sanctioned. Returns ranked POSSIBLE matches with the official designation details (regime, type, sanctions imposed, statement-of-reasons snippet). CRITICAL: this is an INDICATIVE name-match only — a match MUST be verifie
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- Code scan12 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 96 days ago8/15
- Maintainer identityregistry namespace matches repository owner7/10
How Sanctionwise compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 53
- more than 44% of 12,191 servers with a package
What its tools let an agent do: 2 read
Install Sanctionwise in Claude Code, Cursor or VS Code
Runs npx -y sanctionwise on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add sanctionwise -- npx -y sanctionwise
What the publisher says
From the Sanctionwise repository's README, as published. We do not edit it. Read it on GitHub
sanctionwise
Verified UK sanctions screening for AI agents — official FCDO UK Sanctions List, not guesses.
Verified, trustworthy data tools for AI agents. "Qiniso" means "truth" in Zulu.
Website · npm · MCP Registry
Ask an LLM "is this person on the UK sanctions list?" and it will answer from stale, fuzzy memory. Designations change constantly and are specific — that's data, not something to recall. sanctionwise screens a name against the official FCDO UK Sanctions List and returns possible matches with their real designation details, or a clean "no match".
⚠️ Read this — what this is and is NOT
- Indicative name-match only. A match is a POSSIBLE match that a human must verify against the official entry (names are widely shared and transliterated). It is not confirmation that the party you mean is the sanctioned party.
- A "no match" is NOT a clearance. It covers the UK (FCDO) list only, screens the name string you pass (not DOBs or aliases you didn't supply), and reflects the dataset's report date, not real-time.
- Not advice. Not legal, compliance, KYC/AML or sanctions advice, and not a substitute for a regulated sanctions-screening process. Every response includes this disclaimer.
Install
{ "mcpServers": { "sanctionwise": { "command": "npx", "args": ["-y", "sanctionwise"] } } }The official UK Sanctions List data is bundled in the package (works offline, out of the box). The tool also auto-refreshes from a weekly-updated GitHub Release on startup — cached locally, no key, no token, no manual step — so it stays current on its own. Every response reports the dataset's report date.
Use it as a library
npm i sanctionwiseimport { screenName, getSanctionsEntry } from "sanctionwise";
screenName("Vladimir Putin");
// { matchCount: 3, results: [{ id: "RUS0251", type: "Individual",
// primaryName: "Vladimir Vladimirovich PUTIN", matchType: "exact",
// regimes: ["The Russia (Sanctions) (EU Exit) Regulations 2019"], sanctions: "Asset freeze|…" }],
// disclaimer: "INDICATIVE NAME-MATCH SCREEN ONLY. …" }
screenName("Acme Quilting Supplies Ltd").matchCount; // 0 — no match (NOT a clearance)
getSanctionsEntry("RUS0251"); // full official entry for a Unique IDMatching folds accents and is case/punctuation-insensitive, and screens primary names and aliases.
Tools — 2
Data & auto-refresh
The data is the official FCDO UK Sanctions List (designated persons, entities and ships under the Sanctions and Anti-Money Laundering Act 2018), published under the Open Government Licence v3.0. scripts/build-data.mjs parses the official CSV into one record per target (all names/aliases grouped); the bundled build currently carries 6,200+ designated targets. A weekly GitHub Action (.github/workflows/refresh-data.yml) re-downloads the list and publishes it as a GitHub Release asset; the installed tool fetches that asset on startup (cached, offline-safe), so it self-updates with no npm token and no manual step. The bundled copy is the offline / first-run fallback.
What it is not
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Sanctionwise: common questions
- Is Sanctionwise MCP server safe?
- Mostly: it is graded B (80/100). Read the Sanctionwise safety report
- How do I install Sanctionwise?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Sanctionwise need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Sanctionwise maintained?
- The last commit was 135 days ago (2026-06-22). The latest release is v0.1.1.
- How does Sanctionwise compare with other MCP servers?
- safety score 80/100 (higher than 60% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.