mcp-vessel-tracking

# @pipeworx/vessel-tracking

Live worldwide ship positions from AIS radio broadcasts. Platform key (aisstream.io), BYO accepted.

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1679+ live data sources.

## Tools

- `live_ships_in_area(...)` — vessels broadcasting right now in a bounding box or around a point, with position, speed, course, navigational status, type, destination and IMO, plus a breakdown by vessel type.
- `live_ship_position(...)` — live position for specific vessels by MMSI.
- `ais_coverage_check(...)` — whether any receiver actually covers a location, so a zero can be read correctly.

## Auth

Platform key (`PLATFORM_AISSTREAM_KEY`), or BYO via `_apiKey`. Free, instant signup at https://aisstream.io.

## Coverage — read this before trusting a zero

aisstream is a community network of **terrestrial** receivers, so coverage follows where volunteers run hardware. Verified 2026-07-27 with a 60-second subscription:

| Region | Vessels heard |
|---|---|
| Mediterranean | 221 |
| English Channel | 50 (30s) |
| Strait of Malacca | 24 (30s) |
| **Persian Gulf / Strait of Hormuz** | **0** |
| **Gulf of Oman** | **0** |
| **Red Sea / Bab el-Mandeb** | **0** |

There is **no coverage of the Gulf or Red Sea**. Satellite AIS — the paid product from Spire/ORBCOMM — is what covers open ocean and unreceivered coasts, and this is not that. Asking about Hormuz returns `coverage: "none"` with a redirect to `chokepoint_status`, never a bare `0`.

The count field is named `vessels_observed`, not `vessel_count`, because it measures what was heard in a listening window rather than what is present. Every zero carries a `coverage` verdict of `confirmed`, `none` or `unconfirmed`.

### Sampling caveat

AIS transmit intervals depend on motion: a vessel underway broadcasts every 2-10 seconds, one at anchor roughly every 3 minutes. Short windows therefore under-count stationary ships. `live_ship_position` is **best effort by nature** — a 35s window found 1 of 8 vessels confirmed transmitting moments earlier — so widen `window_seconds` (max 40; beyond that callers time out) or use `vesselfinder_vessel` for a stored last-known position.

## Data sources

- Stream: `wss://stream.aisstream.io/v0/stream`

## Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

```json
{
  "mcpServers": {
    "vessel-tracking": {
      "url": "https://gateway.pipeworx.io/vessel-tracking/mcp"
    }
  }
}
```

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/vessel-tracking/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:

```json
{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}
```

Both URLs reach the same gateway and the same 1679+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.

## No MCP client? Call it over HTTP

```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/live_ships_in_area \
  -H 'Content-Type: application/json' \
  -d '{"latitude":43.3,"longitude":5.4,"radius_km":50}'
```

No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/live_ships_in_area`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.

## Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no
gateway round-trip:

```json
{
  "mcpServers": {
    "vessel-tracking": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-vessel-tracking"]
    }
  }
}
```

Or run it directly to confirm it starts:

```bash
npx -y @pipeworx/mcp-vessel-tracking
```

It speaks MCP over stdin/stdout and answers `initialize`/`tools/list`/`tools/call`
for **only** this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.

## Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:

```
ask_pipeworx({ question: "your question about Vessel Tracking data" })
```

The gateway picks the right tool and fills the arguments automatically.

## More

- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)

## License

MIT