Skip to main content
Glama

Live Ships In Area

live_ships_in_area
Read-onlyIdempotent

Live ship positions right now in a geographic area, from AIS radio broadcasts, what vessels are sailing near a port, coastline, strait or set of coordinates at this moment. Returns each vessel heard with its position, speed, course, navigational status, type, destination and IMO where broadcast, plus a breakdown by vessel type (cargo, tanker, passenger, fishing, tug). Give either a centre point (latitude + longitude + radius_km) or a bounding box. COVERAGE IS PARTIAL AND TERRESTRIAL, there is no receiver coverage in the Persian Gulf, Strait of Hormuz, Gulf of Oman or Red Sea, so this tool cannot answer questions about those waters (use chokepoint_status for Hormuz/Suez/Bab el-Mandeb transit counts instead). Counts are vessels heard during a listening window of a few seconds, not a complete count of vessels present.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "latitude": 43.3,
      "longitude": 5.4,
      "radius_km": 50
    },
    "name": "live_ships_in_area"
  }
}

Input Schema

NameRequiredDescriptionDefault
eastNoBounding box eastern longitude
westNoBounding box western longitude
limitNoMaximum vessels to return (default 50, max 300)
northNoBounding box northern latitude
southNoBounding box southern latitude (alternative to centre+radius)
_apiKeyNoaisstream.io API key (free at aisstream.io)
latitudeNoCentre latitude, e.g. 43.3 for Marseille
longitudeNoCentre longitude, e.g. 5.4 for Marseille
radius_kmNoRadius around the centre point in km (default 50, max 500)
ship_typeNoOptional filter on decoded type, e.g. "tanker", "cargo", "passenger", "fishing", "tug"
window_secondsNoHow long to listen, 3-25 seconds (default 12). Longer windows hear more vessels, especially anchored ones which only transmit every ~3 minutes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "_apiKey": "your-vessel-tracking-api-key",
      -    "latitude": 43.3,
      -    "longitude": 5.4,
      -    "radius_km": 50
      -  },
      -  {
      -    "_apiKey": "your-vessel-tracking-api-key",
      -    "east": 0.1,
      -    "north": 51.5,
      -    "ship_type": "tanker",
      -    "south": 51.4,
      -    "west": -0.1,
      -    "window_seconds": 20
      -  }
      -]New value: +[
      +  {
      +    "latitude": 43.3,
      +    "longitude": 5.4,
      +    "radius_km": 50
      +  },
      +  {
      +    "east": 0.1,
      +    "north": 51.5,
      +    "ship_type": "tanker",
      +    "south": 51.4,
      +    "west": -0.1,
      +    "window_seconds": 20
      +  }
      +]
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, no-destructive, open-world, but the description adds substantial context they cannot: partial terrestrial-only coverage, a specific geographic blackout list, and the crucial caveat that counts reflect a multi-second listening window rather than all vessels present. That last point directly prevents an agent from over-claiming completeness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what it returns, then the locator options, then the coverage caveat. Some mild repetition ('right now' / 'at this moment') but each sentence carries distinct operational information, including the non-obvious coverage exclusion.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, no-output-schema tool, the description covers return payload, locator alternatives, listening-window semantics and coverage limits. An agent can decide, parameterize and correctly caveat results from this text alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3, but the description adds the either/or constraint between centre+radius and bounding box — an agent-relevant rule the schema (0 required params) does not enforce. It does not re-explain limit, ship_type or window thresholds beyond the schema's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (live ship positions from AIS radio broadcasts) and enumerates the returned fields (position, speed, course, status, type, destination, IMO) plus a type breakdown. The coverage sentence naming chokepoint_status makes it distinguishable from the sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the two accepted query shapes (centre+radius or bounding box) and, unusually, an explicit when-NOT-to-use clause: no receiver coverage in the Persian Gulf, Strait of Hormuz, Gulf of Oman or Red Sea, with chokepoint_status named as the alternative for those waters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.