@arcnautical/mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARCNAUTICAL_API_KEY | No | Enables the keyed tools (screen_vessel, screen_vessels, get_screening, score_voyage, get_usage). Optional: two tools need no API key at all. | |
| ARCNAUTICAL_BASE_URL | No | Override the base URL for testing. | https://arcnautical.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_vesselA | 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). |
| find_portA | 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. |
| screen_vesselA | 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. |
| screen_vesselsA | 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. |
| get_screeningA | Fetch a stored screening record by id — the audit copy, retained ten years. Needs ARCNAUTICAL_API_KEY. |
| score_voyageA | 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. |
| get_usageB | Live and test usage, remaining allowance, reset time, batch limits and monitor capacity for the configured key. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
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.
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.
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.
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.