Skip to main content
Glama

@arcnautical/mcp

An MCP server for the ArcNautical API: screen any commercial vessel by IMO number for sanctions, ownership opacity and a vetting grade — from Claude, ChatGPT, Cursor, VS Code, Windsurf or any MCP client.

Two tools need no API key at all. Add it, ask "is IMO 9274446 sanctioned?", get the answer.

Smithery npm Wellknown: live

Two ways to use it: a remote endpoint at https://mcp.arcnautical.com/mcp (nothing to install — claude.ai, ChatGPT, Claude Code, Cursor) or a local server over stdio with npx -y @arcnautical/mcp (Claude Desktop and every other stdio client).

IMO 9274446 HS STAR: sanctions RED — 4 confirmed matches on vessel identifier.
Ownership opacity MEDIUM. Vetting grade E (unacceptable). Checked 2026-09-12T08:10:40Z.

Remote endpoint (no install)

https://mcp.arcnautical.com/mcp — MCP Streamable HTTP, stateless, JSON responses. No authentication is required for check_vessel and find_port; the keyed tools take your API key as an Authorization: Bearer header on the MCP request (an X-API-Key or arcnautical-api-key header is accepted too, for gateways that name the header themselves — never a query parameter).

claude.ai — Settings → Connectors → Add custom connector → URL https://mcp.arcnautical.com/mcp, no authentication. The two keyless tools are available at once.

ChatGPT — Settings → Connectors → Create (developer mode) → server URL https://mcp.arcnautical.com/mcp, no authentication.

Claude Code

claude mcp add --transport http arcnautical https://mcp.arcnautical.com/mcp
claude mcp add --transport http arcnautical https://mcp.arcnautical.com/mcp --header "Authorization: Bearer arc_live_…"

Cursor — .cursor/mcp.json:

{
  "mcpServers": {
    "arcnautical": {
      "url": "https://mcp.arcnautical.com/mcp",
      "headers": { "Authorization": "Bearer arc_live_…" }
    }
  }
}

Anything with curl — the endpoint is plain JSON-RPC over POST:

curl -s https://mcp.arcnautical.com/mcp -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_vessel","arguments":{"imo":"9274446"}}}'

The remote endpoint is a thin client of the same public API: a keyless call counts against your 100-per-hour allowance (the caller's address is forwarded), and a keyed call is metered on your key exactly as a direct API call would be. GET /mcp answers 405 — there is no server-to-client stream to hold — and GET https://mcp.arcnautical.com/health reports the endpoint's version.

Related MCP server: Maritime Vessel Data MCP Server

Local server (stdio)

Requires Node 18+. No install step — every client below runs it with npx.

Claude Desktop — claude_desktop_config.json:

{
  "mcpServers": {
    "arcnautical": {
      "command": "npx",
      "args": ["-y", "@arcnautical/mcp"]
    }
  }
}

Claude Code

claude mcp add arcnautical -- npx -y @arcnautical/mcp

Cursor / Windsurf / VS Code — same command / args shape in the client's MCP settings.

To unlock the full record, batches and voyage scoring, add an API key to the env block:

{
  "mcpServers": {
    "arcnautical": {
      "command": "npx",
      "args": ["-y", "@arcnautical/mcp"],
      "env": { "ARCNAUTICAL_API_KEY": "arc_live_…" }
    }
  }
}

Keys are free and self-serve at https://arcnautical.com/get-a-key?from=mcp — no card, no approval step. A new key includes a one-time free allowance of vessel screenings and a monthly allowance of voyage assessments; get_usage reports both, and the current numbers are on arcnautical.com/developers.

Tools

Tool

Key?

What it does

check_vessel

no

Sanctions status (OFAC SDN, EU, UN, UK OFSI, OpenSanctions), ownership-opacity score, A–E vetting grade for one IMO. 100/hour per IP.

find_port

no

Resolve a port name or country to UN/LOCODEs — call before score_voyage.

screen_vessel

yes

The full screening record: every match with its source list, programme and confidence class, the graded vetting factors, per-source freshness, a retained record id. Same hull asked again today replays free.

screen_vessels

yes

Batch up to 50 IMOs and wait for the results.

get_screening

yes

Retrieve a stored record by id (retained ten years).

score_voyage

yes

Route risk between two LOCODEs: score, level, drivers, confidence, missing sources.

get_usage

yes

Remaining allowance and limits for the configured key.

Reading a verdict

  • RED — confirmed match on the vessel identifier. AMBER — possible match, review it. GREEN — no match against the sources reached. INCOMPLETE — a core source could not be read; never present it as clear.

  • coverage_complete: false on a GREEN means one supplementary list was unavailable: re-screen before relying on it.

  • assessed: false means ownership and vetting are defaults, not findings.

  • The keyless check matches the vessel's current name and identifiers only. A hull renamed after a designation can read GREEN there; screen_vessel covers that case.

  • Designations change daily. Quote the checkedAt / screened_at time with any answer.

Idempotency

Every resource-creating call sends an Idempotency-Key derived from the question — the hull and the UTC day — not from the attempt. Asking about the same vessel twice in a day returns the stored record and spends nothing. The API's docs measured 42% of one integration's monthly screenings as same-day repeats billed only because their client generated a random key per call; this server does not do that.

Environment

Variable

Default

Purpose

ARCNAUTICAL_API_KEY

unset

Enables the keyed tools (stdio; the remote endpoint reads the Authorization header instead).

ARCNAUTICAL_BASE_URL

https://arcnautical.com

Override for testing.

PORT / HOST

3005 / all interfaces

--http only.

MCP_TRUST_PROXY

unset

--http only: 1 reads the caller's address from X-Real-IP / CF-Connecting-IP set by a reverse proxy. Only when nothing but the proxy can reach the port.

Self-hosting the HTTP endpoint

npx -y @arcnautical/mcp --http serves POST /mcp on port 3005 — useful when your assistants run in a network that cannot spawn local processes but can reach one internal URL. The Dockerfile in this repository builds the same thing; it is what mcp.arcnautical.com runs.

Development

npm install
npm test        # builds, then drives dist/cli.js over stdio AND createHttpServer() over Streamable HTTP
                # (a local stub API asserts the forwarded caller address and Bearer key; one call hits prod keyless)
npm run start:http   # the remote endpoint on http://localhost:3005/mcp

MIT © ArcNautical

Available Tools

7 tools
check_vesselCheck a vessel (no key)A
Read-onlyIdempotent
Inspect

Screen one vessel by IMO number against OFAC SDN, EU, UN, UK OFSI and OpenSanctions, with an ownership-opacity score and an A–E vetting grade from port-state-control history. Works with no API key. Rate-limited to 100 requests per hour per IP. Returns the VERDICT SUMMARY only; for every sanctions match with its source list and confidence class use screen_vessel (needs a key).

Inputs: imo (required).

find_portFind a port / UN/LOCODE (no key)A
Read-onlyIdempotent
Inspect

Resolve a port name, country or partial UN/LOCODE to the LOCODEs the routing engine knows. Routes are addressed by LOCODE, so call this before score_voyage rather than guessing a code. Works with no API key.

Inputs: query (required), limit.

get_screeningRetrieve a screening record (API key)A
Read-onlyIdempotent
Inspect

Fetch a stored screening record by id — the audit copy, retained ten years. Needs ARCNAUTICAL_API_KEY.

Inputs: id (required).

get_usageUsage and quota (API key)B
Read-onlyIdempotent
Inspect

Live and test usage, remaining allowance, reset time, batch limits and monitor capacity for the configured key.

Inputs: no named parameters.

score_voyageScore a voyage route (API key)A
Idempotent
Inspect

Route risk between two ports (UN/LOCODEs): a 0–100 score, risk level, the signals driving it (war-risk areas, piracy, chokepoints, weather, sanctions exposure of transited EEZs), confidence and any missing sources. Resolve port names with find_port first. Needs ARCNAUTICAL_API_KEY; 10,000 assessments a month are included with a self-serve key.

Inputs: origin (required), destination (required), dwt_tonnes, speed_knots, +3 more.

screen_vesselScreen a vessel (full record, API key)A
Idempotent
Inspect

The authenticated screening record for one vessel: every sanctions match with its source list, programme and confidence class, ownership opacity, the graded vetting factors, per-source freshness, and a retained record id. Needs ARCNAUTICAL_API_KEY. Metered: 5,000 live screenings a month are included with a self-serve key. The same vessel asked again on the same day replays the stored record free. If the result is INCOMPLETE for identity, call again with vessel_name.

Inputs: imo (required), vessel_name, include_vetting, customer_reference.

screen_vesselsScreen up to 50 vessels (API key)A
Idempotent
Inspect

Batch-screen a list of IMO numbers and wait for the results (up to two minutes). Returns one verdict per hull plus the batch status. Needs ARCNAUTICAL_API_KEY. Each hull spends one screening unit unless it was already screened today.

Inputs: imos (required), include_vetting.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 7 tools

    Disambiguation4/5

    check_vessel, screen_vessel and screen_vessels all screen vessels and could be confused, but the descriptions explicitly differentiate them (free summary vs. authenticated full record vs. batch) and even point callers from check_vessel to screen_vessel. find_port, get_screening, get_usage and score_voyage are clearly distinct.

    Naming Consistency4/5

    Names consistently use snake_case verb_noun (get_screening, find_port, screen_vessel, score_voyage). The only deviation is the mixed verb choice 'check' vs 'screen' for the same core action and the singular/plural screen_vessel vs screen_vessels pair, which is a minor blemish.

    Tool Count5/5

    Seven tools is well-scoped for a maritime sanctions-screening server, with each tool earning its place (single screening, batch screening, record retrieval, port resolution, voyage scoring, usage). No redundant or filler tools.

    Completeness4/5

    Covers the core lifecycle: resolve ports, screen vessels individually and in batch, retrieve retained records, score voyage risk and check usage. Minor gaps exist — get_usage references monitor capacity but no tool manages monitors, and there is no tool to list or export past screenings.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables real-time vessel tracking, port data, maritime weather, and maritime intelligence through 25 tools, allowing AI clients to query live vessel positions, registry, port info, area searches, weather, and more.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Real-time OFAC and global sanctions screening for AI agents: screen crypto addresses, emails, websites, government IDs, and countries against OFAC SDN and 10+ sanctions/crime/risk lists, plus PEP screening, VPN detection, and IP geolocation. Hosted remote streamable-HTTP server at https://api.compliapi.com/mcp (anonymous tools/list; free API key or x402 pay-per-call).
      MIT