arcnautical

endpoint

https://mcp.arcnautical.com/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is arcnautical live?

Yes — it answered the hub's last check (checked 6m ago). It answered 100% of checks over the last 30 days.

Is arcnautical free to use?

Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.

What tools does arcnautical have?

7 tools: screen_vessel, screen_vessels, score_voyage, check_vessel, get_screening, find_port, get_usage.

Is arcnautical safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• get_usage reads auth-required 6h ago

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

  mcp-tool

  12345

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

  arguments 5 lines copy
• screen_vessel reads unknown never probed

  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 a one-time free allowance of live screenings; get_usage reports what is left. 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.

  mcp-tool

  123456789101112131415161718192021222324252627282930

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

  arguments 30 lines copy
• screen_vessels reads unknown never probed

  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.

  mcp-tool

  12345678910111213141516171819202122232425

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

  arguments 25 lines copy
• score_voyage reads unknown never probed

  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), sea days, confidence and any missing sources. On lanes that can go either way round Africa it also scores the other passage (Suez or Cape) in `alternatives`. Resolve port names with find_port first. Needs ARCNAUTICAL_API_KEY; see get_usage for the allowance.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "origin",
      "destination"
    ],
    "properties": {
      "origin": {
        "type": "string",
        "pattern": "^[A-Za-z]{5}$",
        "description": "Origin UN/LOCODE, e.g. NLRTM"
      },
      "passage": {
        "enum": [
          "shortest",
          "suez",
          "cape"
        ],
        "type": "string",
        "description": "Which way round Africa to score: shortest (default; Suez on Asia-Europe), suez or cape. Refused on lanes with no such passage"
      },
      "dwt_tonnes": {
        "type": "number",
        "maximum": 600000,
        "minimum": 1,
        "description": "Deadweight in tonnes; accepted, but it does not change the score today"
      },
      "destination": {
        "type": "string",
        "pattern": "^[A-Za-z]{5}$",
        "description": "Destination UN/LOCODE, e.g. CNSHA"
      },
      "speed_knots": {
        "type": "number",
        "maximum": 25,
        "minimum": 8,
        "description": "Planned service speed, 8-25 knots; sets route.transit_days (default 14), and with vessel_type times the weather"
      },
      "vessel_type": {
        "enum": [
          "container",
          "bulk",
          "tanker",
          "lng",
          "general"
        ],
        "type": "string",
        "description": "Vessel class; changes which threat signals weigh most (default: general)"
      },
      "load_condition": {
        "enum": [
          "laden",
          "ballast"
        ],
        "type": "string",
        "description": "laden or ballast; affects exposure on the transit (with vessel_type)"
      },
      "customer_reference": {
        "type": "string",
        "maxLength": 128,
        "description": "Your own reference (voyage id, fixture); echoed on the assessment"
      }
    },
    "additionalProperties": false
  }

  arguments 66 lines copy
• check_vessel reads unknown 6h ago

  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).

  mcp-tool

  123456789101112131415

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

  arguments 15 lines copy
• get_screening reads unknown 6h ago

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

  mcp-tool

  123456789101112131415

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

  arguments 15 lines copy
• find_port reads unknown 23h ago

  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.

  mcp-tool

  123456789101112131415161718192021

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

  arguments 21 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.