Power your agent
पब्लिशर की अपनी कमांड। PlugMCP एंडपॉइंट नहीं।
Host a copy with our keys and logs.
npx -y @cyanheads/[email protected]Claude Code में लोकल कमांड के लिए इंस्टॉल लिंक नहीं है। नीचे दी गई कमांड कॉपी करें और टर्मिनल में चलाएँ।
claude mcp add cyanheads-sanctions-screening-mcp-server -- npx -y @cyanheads/sanctions-screening-mcp-server@0.5.1टर्मिनल में चलाएँ।
{ "mcpServers": { "cyanheads-sanctions-screening-mcp-server": { "command": "npx", "args": [ "-y", "@cyanheads/[email protected]" ] } }}claude_desktop_config.json
रिमोट URL या आपकी मशीन पर कमांड? दोनों इंस्टॉल में क्या अंतर है
PlugMCP पर चलाएँ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
लॉन्चPublic Hosted Server: https://sanctions-screening.caseyjhand.com/mcp
Sanctions screening and legal-entity resolution over the consolidated OFAC, EU, UK, and UN lists plus the GLEIF LEI registry, matched offline against a local mirror. Screen a name for potential watchlist hits, resolve a company to its LEI, and trace its ownership chain.
[!IMPORTANT] A screening aid, not a compliance determination. Every result is a potential match with a transparent score and source provenance, never a verdict. A hit is a candidate to verify against the official source; an empty result is never a clearance. Sanctions compliance needs human review and a qualified determination. This server feeds that process and does not perform it.
All resource data is also reachable through the tools, for clients that don't surface resources.
sanctions_screen_name toolname in any script (at most 64 words and 1,024 characters) plus optional sources, entityType, and minScore filters; matchMode is strict (default) or fuzzy. Strict runs a fuzzy pass over each selected list it finds nothing on: a full pass when it finds nothing on any list, otherwise one that adds, after the strict hits, only candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf. fuzzySources names the lists a fuzzy pass searched; up to 100 hits per page (limit, default 25) with offsetsource, sourceEntryId, the list's published referenceNumber where it has one, matchedName with its matchedNameType, and matchType (exact / strong / approximate); approximate hits add the raw Jaro-Winkler score (0–1) and queryTokenCoveragesources names every selected list a hit's party is on. OFAC publishes a party on the SDN List and a non-SDN list under one entry ID in both of its files; with both OFAC lists selected that party is one hit, counted once, naming both even when the screen matched one record. Its other fields, the designation date included, come from the source record: ofac_sdn, unless the Consolidated record matched alone or bettertotalAvailable, hasMore, and nextOffset page the rest, and paging reaches every match counted; totalAvailableBasis marks the count exact (strict matched on every selected list) or a lower_bound (a fuzzy pass ran), and a notice asks for a more distinctive word when a list's fuzzy candidate pool reached its budgetsanctions_screen_identifier toolvalue (an identifier as you hold it) plus optional type (any default, imo, swift_bic, digital_currency_address, passport, national_id) and sources- . / are ignored; an IMO number matches with or without its IMO prefix; a SWIFT/BIC compares on its first eight characters, so a branch BIC11 matches its institution's BIC8; a wallet address folds case only for hex (0x…), bech32 (bc1…, ltc1…, bnb1…), and cashaddr encodings, while base58 addresses compare exactlytype matches on each list's published label: imo is OFAC Vessel Registration Identification, UK IMO Number, and EU IMO (vessel identification); swift_bic is SWIFT/BIC and SWIFT BIC; digital_currency_address is OFAC Digital Currency Address - <code>; passport and national_id cover the lists' passport and national-ID labels. any also reaches every label with no category (MMSI, call signs, tail numbers, tax and registration numbers, email, websites)matchedIdentifiers that matched as published and its sources, an OFAC party on both OFAC lists being one hit naming both; not paged. An identifier a list prints only in free-text remarks, or bundled with other numbers in one field, does not matchsanctions_get_designation toolsource (ofac_sdn, ofac_consolidated, eu, uk, un) and entryId: the sourceEntryId from a screening hit, or the reference number the list publishes (UN QDe.004, EU EU.27.28, UK OFSI Group ID 14196). Matched trimmed and case-insensitive, entry ID first; a reference number two designations share fails as reference_ambiguous, naming bothreferenceNumber beside sourceEntryId where the list publishes one; OFAC publishes none, its entry ID being its published number1952-10-07, 1946-08, 1938, or an interval such as 1955/1957), with circa: true where the source marks one approximate; designationDate is the source's own designation date as YYYY-MM-DDofac_sdn, the non-SDN lists for ofac_consolidated, earliest first. A party on both files can carry a different date on eachlegalBasis is the instrument the list cites, verbatim: OFAC's legal-basis references (Executive Order 14024 (Russia)), the EU regulation title (2024/1488 (OJ L27052024)), or the UK regime's regulations (The Russia (Sanctions) (EU Exit) Regulations 2019), several joined with ; . The UN list publishes nonefeatures carries what a list publishes to describe the party rather than identify it, each typed with the list's own label, in published order: OFAC's vessel flag, type, owner, and tonnage, aircraft model, operator, and manufacture date, title, gender, and sanctions notes (Secondary sanctions risk: See Section 11 of Executive Order 14024.), and the UK list's ship details (CurrentBelievedFlagOfShip, TypeOfShip, YearBuilt, …). A date is ISO 8601 at published precision, with circa: true where OFAC marks it approximate. The EU and UN lists contribute none, and no screening tool matches a feature valuesanctions_resolve_entity toolname in any script (same bound as sanctions_screen_name) plus optional jurisdiction, status, and minScore; matchMode is strict (default), which falls back to a fuzzy pass only when strict finds nothing, or fuzzy; up to 50 candidates per page (limit, default 10) with offsetjurisdiction is a country code, which matches the country and every subdivision under it (US matches US-DE and US-CA), or an ISO 3166-2 subdivision code (US-DE), matched exactly; case-insensitivestatus: issued (default) matches ISSUED, lapsed matches exactly LAPSED, and any applies no filter — the only way to reach RETIRED, DUPLICATE, ANNULLED, PENDING_TRANSFER, PENDING_ARCHIVAL, or MERGED records, each candidate's status naming its statelei, legalName, the matchedName and its matchedNameType (LEGAL_NAME, PREVIOUS_LEGAL_NAME, TRADING_OR_OPERATING_NAME, …, or UNKNOWN for a name stored without a type), and matchType, with score and queryTokenCoverage on approximate matches; one candidate per LEI, paged by the same totalAvailable / totalAvailableBasis / hasMore / nextOffset fieldssanctions_get_entity toollei; returns the legal name, otherNames, legal and headquarters addresses, status, jurisdiction, registration authority, and lastUpdatealternateNames lists every other and transliterated name with its GLEIF type; a name the mirror stored before types were kept reads as UNKNOWNsanctionsHits cross-references the entity against every watchlist: the legal name and every alternateNames entry screened strict (exact, then all tokens present, never fuzzy), and the LEI and registrationAuthorityEntityId looked up exactly as non-document identifiers (never passports, national IDs, IMO numbers, SWIFT/BIC codes, or wallets). The registration number matches only an identifier published for the country of the entity's jurisdiction, and is skipped when the entity publishes no jurisdiction or a not-available placeholder (N/A, n.a.) in place of a numbersources names both, exact name and identifier matches first, then strong name matches, capped at 25 after the merge. matchedOn lists every input that produced a hit (legal_name, other_name with its GLEIF type, lei, registration_number); an identifier match adds matchedIdentifiers as the list publishes them, and a hit no name produced carries no matchedName or matchType. No hit carries a score: only an approximate (fuzzy) match has one, and every screen here is strictscreeningStatus (screened / not_ready) says whether the cross-reference ran; sanctionsScreen counts distinct designations across every input (totalAvailable), flags a capped list (hasMore), and lists in screenedInputs what was screened beyond the always-screened legal name and LEIsanctions_trace_ownership toollei, direction (parents / children / both, default both), and depth 1–5 (default 3); screenNodes: true cross-references every node as sanctions_get_entity does (its names strict, its LEI and country-matched registration number as identifiers), up to 10 merged hits per node; a node with no Level 1 record has no name to screen and is looked up by its LEI alone. both is a parents walk plus a children walk from the root, each to depth; it never reaches siblings or co-parentsnodes (with role and depth) and edges (with relationshipType, each joining two returned nodes); role is the side that reached the node. depth counts every relationship type except IS_ULTIMATELY_CONSOLIDATED_BY, a shortcut to the top of the group: a node only that edge reaches within depth is an unwalked leaf flagged reachedVia: "ultimate", its depth that one hop. complete is false when the graph is truncated (relationships past the depth limit, or links of a flagged leaf, that it does not show; an ultimate-parent edge counts only when it leads to an entity the graph does not return) or missingEntityLeis lists nodes with no Level 1 record. It covers the loaded relationships only, and most entities publish no parent relationship.parentStatus.direct / .ultimate: relationship, exception (a GLEIF reporting exception, with every reason, such as NATURAL_PERSONS), none, or unknown. unknown means exception data is not loaded, which reportingExceptionsLoaded: false states.screeningStatus (screened / not_requested / not_ready), screenedNodeCount, and flaggedNodeCount; each screened node carries its own sanctionsScreen (hasMore, screenedInputs) and hits with matchedOn and matchedIdentifiers, in the sanctions_get_entity shapesanctions_list_sources toolgleif, each with recordCount, url (the configured source URL), and license; the gleif row's recordCount is Level 1 entities and its relationshipCount Level 2 ownership relationshipssanctionsReady / sanctionsAsOf and leiReady / leiAsOf report whether each mirror has synced and when; sanctionsAsOf is the last sync in which every sanctions list refreshed. Not gated on readiness, so it reports an empty mirror instead of failingreportingExceptionsLoaded, and on the gleif row a reportingExceptionCount once the reporting exceptions are loadedalternateNamesIndexed: whether GLEIF's trading, previous, alternative-language, and transliterated names are indexed; until mirror:init builds the index, sanctions_resolve_entity searches legal names onlysanctions://designation/{source}/{entryId} resourcesource is one of the five list codes, entryId the list's own ID or its published reference number, resolved as sanctions_get_designation resolves it and decoded once when percent-encoded; returns the sanctions_get_designation payload as application/jsonprivatesanctions://entity/{lei} resourcesanctions_get_entity Level 1 payload for one lei, without the sanctions cross-reference, which is tool-onlyprivatesanctions://sources resourcesanctions_list_sources payload, unchangedttlMs: 0: never cached, because readiness and the as-of timestamps are the payloadsanctions_vet_counterparty promptname required; jurisdiction optional (a country code, which includes its subdivisions, or an ISO 3166-2 subdivision code)sanctions_screen_identifier), resolves it to an LEI, traces ownership with screenNodes: true, pulls each hit's designation record, and asks for a summary that treats every match as a candidate to verify and says, from matchedOn, which of the entity's names or identifiers produced it. It names GLEIF parents as accounting-consolidation parents, not beneficial owners, and reports a reporting exception's reasons rather than reading it as "no parent"Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.
Sanctions-screening-specific:
MirrorServiceAgent-friendly output:
score and a literal queryTokenCoverage count, never a blended confidence; every hit names its list, program, designation date, and the name that matched, typed primary / aka / fka / low-quality-akacaveat in the output of sanctions_screen_name, sanctions_screen_identifier, sanctions_get_designation, sanctions_get_entity, and sanctions_trace_ownershiptotalAvailableBasis, screeningStatus, complete / truncated / missingEntityLeis, and each node's parentStatus say what a response did not covermirror_not_ready (retryable) until its mirror is loaded; unknown IDs fail as designation_not_found or lei_not_found, an LEI the mirror lacks whose ISO 17442 check digits fail as invalid_lei_checksum (a mistyped character), and a reference number two designations share as reference_ambiguous; a name with no letter or digit fails as name_not_searchable, one past the length bound as name_too_long, and an identifier with nothing left once spacing and separators are removed as identifier_not_searchableA public instance is available at https://sanctions-screening.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:
{
"mcpServers": {
"sanctions-screening-mcp-server": {
"type": "streamable-http",
"url": "https://sanctions-screening.caseyjhand.com/mcp"
}
}
}
Add the following to your MCP client configuration file. The mirror is not bundled, and the npm package cannot build it: run bun run mirror:init from a clone (Installation) or inside the Docker image, then point SANCTIONS_MIRROR_PATH at the result (see Mirror lifecycle).
{
"mcpServers": {
"sanctions-screening-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/sanctions-screening-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with npx (no Bun required):
{
"mcpServers": {
"sanctions-screening-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/sanctions-screening-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
For Streamable HTTP, set the transport and start the server:
MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp
git clone https://github.com/cyanheads/sanctions-screening-mcp-server.git
cd sanctions-screening-mcp-server
bun install
cp .env.example .env
# edit .env if you need to override defaults (all optional)
bun run mirror:init
Every source is keyless, so nothing here is required.
See .env.example for the full list of optional overrides.
Build and run:
# One-time build
bun run rebuild
# Run the built server
bun run start:stdio
# or
bun run start:http
Run checks and tests:
bun run devcheck # Lint, format, typecheck, security, changelog sync
bun run test # Vitest test suite
bun run lint:mcp # Validate MCP definitions against spec
The mirror loads out-of-band, never on the request path.
On HTTP deployments, the scheduled refresh runs in a separate process using the serving runtime and its runtime arguments. SQLite WAL keeps committed indexes readable while that child writes, so health and screening requests continue during a rebuild. Timeout or shutdown requests cancellation, allows up to 5 seconds for cleanup, then kills and awaits a child that has not exited. Every terminal outcome releases the slot for the next tick. A killed run can leave committed harvest pages behind; the next successful refresh rebuilds their derived indexes before completing. The serving process reads updated freshness and reporting-exception counts without a restart.
A list that fails to download or arrives truncated keeps its stored rows and removes nothing, while every other list still refreshes and the name and identifier indexes are rebuilt. GLEIF still refreshes after it, and the run then exits non-zero naming each failed list (ofac_sdn, eu, …). sanctionsAsOf advances only on a run in which every list refreshed, and a first mirror:init with a failed list leaves the mirror not ready.
GLEIF advances all at once or not at all. leiAsOf and the checkpoint move only after every dataset's covering delta has applied, so an interrupted refresh leaves both where they were, and the next run re-applies from the same point. Two cases apply nothing to GLEIF, leave leiAsOf unchanged, and exit non-zero naming mirror:init: a checkpoint older than the one-month window, and a mirror with no checkpoint. Every mirror written by 0.3.0 or earlier has no checkpoint, so run mirror:init once after upgrading. Until then, traces read unpublished parents as unknown, and sanctions_resolve_entity searches legal names only, with a notice saying alternate names are not yet indexed; its fuzzy pass then blocks on the first three distinctive words of a longer name and says its candidate bound was reached. 0.3.0 stored other names without their types and no transliterated names at all, so the name index is built from the golden copy mirror:init loads, never from the stored rows. Every GLEIF write after that keeps the index current. A GLEIF write by an earlier release, after a rollback, leaves it behind, and resolution returns to legal names and the notice until the next mirror:init.
A mirror written by an earlier release upgrades in place on first open: the designation table gains its reference_number column, the sanctions name index is rebuilt from the stored designations before the first screen (about 4 s on the 2026-10-03 lists), and the identifier index is built from the stored records before the first lookup, so sanctions_screen_identifier answers from a populated mirror without a re-init. What the earlier release did not read, or read wrongly — reference numbers, the OFAC and UK identifiers beyond identity documents, dates at published precision, OFAC designation dates taken from each file's own lists, legalBasis, and features — arrives with the next sanctions refresh, which rewrites every stored designation, so run mirror:refresh after upgrading rather than waiting for the cron. Until then sanctions_get_designation returns features: [] for every stored record, and a placeholder an earlier release stored as an identifier (the UK's N/A passport) still matches in sanctions_screen_identifier. The same mirror:refresh builds the GLEIF exact-name index when its GLEIF leg runs; until then a strict resolution that reaches its 2,000-name bound runs without it and misses an exact name the scan did not reach. The identifier index is also rebuilt on open whenever a sync it did not follow has changed the stored records, such as one an earlier release ran after a rollback. The GLEIF mirror's first open drops the lei_entity status index, which no resolution query reads: about 2 s on the full corpus, freeing ~54 MiB that later writes reuse. The file shrinks only after a manual VACUUM.
Every leg of mirror:init and mirror:refresh streams in bounded batches, so peak memory tracks the batch size, not the source size. The sanctions XML totals about 172 MB. The GLEIF Level 1 golden copy is about 3.4M records (~890 MB compressed) and dominates disk use; its name index (~4M names) adds about 0.8 GB of that. The reporting exceptions add about 6.4M rows (~525 MiB on disk).
docker build -t sanctions-screening-mcp-server .
docker run --rm -p 3010:3010 -v sanctions-data:/usr/src/app/data sanctions-screening-mcp-server
The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/sanctions-screening-mcp-server. Mount a volume at /usr/src/app/data so the mirror survives restarts, and populate it with bun run mirror:init via docker exec. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.
See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:
try/catch in tool logicctx.log for request-scoped logging; the mirror is reached through getScreeningService(), not ctx.statesrc/mcp-server/*/definitions/index.tsThis server redistributes open data from these sources, cited per their terms:
UKSL has been the single authoritative UK source since the OFSI Consolidated List closed on 28 January 2026.
Issues are welcome. Run checks and tests before submitting:
bun run devcheck
bun run test
Apache-2.0 — see LICENSE for details.
Screen names against the consolidated OFAC, EU, UK, and UN sanctions lists and resolve legal entities against GLEIF, fuzzy-matched offline over a local SQLite + FTS5 mirror. A screening aid, not a com
{ "mcpServers": { "cyanheads-sanctions-screening-mcp-server": { "command": "npx", "args": [ "-y", "@cyanheads/[email protected]" ] } }}ओवरव्यू
Screen names against the consolidated OFAC, EU, UK, and UN sanctions lists and resolve legal entities against GLEIF, fuzzy-matched offline over a local SQLite + FTS5 mirror. A screening aid, not a compliance determination.
टूल
अभी टूल सूची नहीं है। रिमोट सर्वर को पहले हेल्थ चेक के बाद सूची मिलती है।
FAQ
इस पेज पर Cursor, Claude Desktop, Claude Code या VS Code के लिए stdio कॉन्फ़िग कॉपी करें। यह पब्लिशर का इंस्टॉल इस्तेमाल करता है, PlugMCP प्रॉक्सी नहीं।
इस रिकॉर्ड में कोई ज़रूरी एनवायरनमेंट वेरिएबल दर्ज नहीं है।
@cyanheads/sanctions Screening stdio पर लोकल चलता है।
पिछली जाँच 2026-10-28 को हुई। Screen names against the consolidated OFAC, EU, UK, and UN sanctions lists and resolve legal entities against GLEIF, fuzzy-matched offline over a local SQLite + FTS5 mirror. A screening aid, not a compliance determination.