com.arcnautical/mcp

Official7 tools

by arcnautical · TypeScript

Screen any vessel by IMO for sanctions, ownership opacity and vetting grade. Keyless check included.

@arcnautical/mcp (com.arcnautical/mcp)

An MCP server for the ArcNautical API that screens any commercial vessel by IMO number for sanctions, ownership opacity, and a vetting grade. It can be used from Claude, ChatGPT, Cursor, VS Code, Windsurf, or any MCP client.

🛠️ Key Features

Vessel screening by IMO number for sanctions
Ownership opacity checks
Vetting grade results
Includes a keyless option: “Two tools need no API key at all”

🚀 Use Cases

Ask an MCP client to check a specific vessel by IMO number
Example query: “is IMO 9274446 sanctioned?”

⚡ Developer Benefits

Works with “any MCP client”
Supports use via common IDE/chat environments (Claude, ChatGPT, Cursor, VS Code, Windsurf)

⚠️ Limitations

Tool behavior depends on whether API keys are provided (“Two tools need no API key at all”; adding a key is referenced for additional access).

Captured live from the server via tools/list.

check_vessel

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).

Parameters1

imo

string

required

Seven-digit IMO number of the vessel

Raw schema

{
  "type": "object",
  "properties": {
    "imo": {
      "type": "string",
      "pattern": "^\\d{7}$",
      "description": "Seven-digit IMO number of the vessel"
    }
  },
  "required": [
    "imo"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

find_port

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.

Parameters2

query	string	required	Port name, country, or LOCODE fragment, e.g. "rotterdam", "NLRTM", "Piraeus"
limit	integer	optional	Maximum matches to return (default 5)

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "description": "Port name, country, or LOCODE fragment, e.g. \"rotterdam\", \"NLRTM\", \"Piraeus\""
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "description": "Maximum matches to return (default 5)"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

screen_vessel

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: a new self-serve key includes 5,000 live screenings once (a one-time allowance). 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.

Parameters4

imo	string	required	Seven-digit IMO number of the vessel
vessel_name	string	optional	Only when a previous screen was INCOMPLETE for identity; a name you can confirm
customer_reference	string	optional	Your own reference (order id, voyage id); echoed on the record
include_vetting	boolean	optional	false skips the vetting grade for a faster sanctions-only screen

Raw schema

{
  "type": "object",
  "properties": {
    "imo": {
      "type": "string",
      "pattern": "^\\d{7}$",
      "description": "Seven-digit IMO number of the vessel"
    },
    "vessel_name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Only when a previous screen was INCOMPLETE for identity; a name you can confirm"
    },
    "customer_reference": {
      "type": "string",
      "maxLength": 128,
      "description": "Your own reference (order id, voyage id); echoed on the record"
    },
    "include_vetting": {
      "type": "boolean",
      "description": "false skips the vetting grade for a faster sanctions-only screen"
    }
  },
  "required": [
    "imo"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

screen_vessels

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.

Parameters2

imos	array	required	Up to 50 seven-digit IMO numbers
include_vetting	boolean	optional	false skips the vetting grade for a faster sanctions-only screen

Raw schema

{
  "type": "object",
  "properties": {
    "imos": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^\\d{7}$",
        "description": "Seven-digit IMO number of the vessel"
      },
      "minItems": 1,
      "maxItems": 50,
      "description": "Up to 50 seven-digit IMO numbers"
    },
    "include_vetting": {
      "type": "boolean",
      "description": "false skips the vetting grade for a faster sanctions-only screen"
    }
  },
  "required": [
    "imos"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_screening

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

Parameters1

string

required

Screening id returned by screen_vessel or in a batch item

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "format": "uuid",
      "description": "Screening id returned by screen_vessel or in a batch item"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

score_voyage

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.

Parameters7

origin	string	required	Origin UN/LOCODE, e.g. NLRTM
destination	string	required	Destination UN/LOCODE, e.g. CNSHA
vessel_type	string	optional	Vessel class; changes which threat signals weigh most (default: general)
load_condition	string	optional	laden or ballast; affects exposure on the transit
speed_knots	number	optional	Planned service speed, 8-25 knots; sets transit time through each risk area
dwt_tonnes	number	optional	Deadweight in tonnes; used for chokepoint and draught constraints
customer_reference	string	optional	Your own reference (voyage id, fixture); echoed on the assessment

Raw schema

{
  "type": "object",
  "properties": {
    "origin": {
      "type": "string",
      "pattern": "^[A-Za-z]{5}$",
      "description": "Origin UN/LOCODE, e.g. NLRTM"
    },
    "destination": {
      "type": "string",
      "pattern": "^[A-Za-z]{5}$",
      "description": "Destination UN/LOCODE, e.g. CNSHA"
    },
    "vessel_type": {
      "type": "string",
      "enum": [
        "container",
        "bulk",
        "tanker",
        "lng",
        "general"
      ],
      "description": "Vessel class; changes which threat signals weigh most (default: general)"
    },
    "load_condition": {
      "type": "string",
      "enum": [
        "laden",
        "ballast"
      ],
      "description": "laden or ballast; affects exposure on the transit"
    },
    "speed_knots": {
      "type": "number",
      "minimum": 8,
      "maximum": 25,
      "description": "Planned service speed, 8-25 knots; sets transit time through each risk area"
    },
    "dwt_tonnes": {
      "type": "number",
      "minimum": 1,
      "maximum": 600000,
      "description": "Deadweight in tonnes; used for chokepoint and draught constraints"
    },
    "customer_reference": {
      "type": "string",
      "maxLength": 128,
      "description": "Your own reference (voyage id, fixture); echoed on the assessment"
    }
  },
  "required": [
    "origin",
    "destination"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_usage

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md8 KBView on GitHub

@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.

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).

code

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

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:

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:

code

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.

Local server (stdio)

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

Claude Desktop — claude_desktop_config.json:

json

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

Claude Code

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:

json

{
  "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 5,000 vessel screenings once (a one-time allowance) and 10,000 voyage assessments a month.

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

code

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

Install

Tools (7)

check_vesselfind_portscreen_vesselscreen_vesselsget_screeningscore_voyageget_usage

Configuration

Environment variables

ARCNAUTICAL_API_KEYsecret

Optional. Self-serve at https://arcnautical.com/get-a-key?from=mcp; unlocks the full screening record, batches and voyage scoring. check_vessel and find_port work without it.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@arcnautical/mcp@0.2.1"
      ],
      "env": {
        "ARCNAUTICAL_API_KEY": "<YOUR_ARCNAUTICAL_API_KEY>"
      }
    }
  }
}

com.arcnautical/mcp

@arcnautical/mcp (com.arcnautical/mcp)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

check_vessel

find_port

screen_vessel

screen_vessels

get_screening

score_voyage

get_usage

@arcnautical/mcp

Remote endpoint (no install)

Local server (stdio)

Tools

Reading a verdict

Idempotency

Environment

Self-hosting the HTTP endpoint

Links

Development

Install

Configuration

Related servers