SkillAgentSearch skills...

maritimeint

AIS vessel tracking & sanctions-evasion anomaly detection

Install / Use

claude mcp add cognis-digital -- npx -y github:cognis-digital/maritimeint

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

76/100

Category

Security

Supported Platforms

Claude Code
Claude Desktop

Our assessment of maritimeint

maritimeint scores 76/100 on our quality scale, 1013th of 1,099 Security skills we index.

Its MCP Server is 32 KB long, well organised into 31 sections with 20 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
8/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so maritimeint is actively maintained.
  • Our last check on 2026-09-20 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 75/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (1 minor note below). An AI review of the same text found nothing harmful.

  • noteInstalls by piping a downloaded script into a shellline 499
    curl -fsSL https://raw.githubusercontent.com/cognis-digital/maritimeint/main/install.sh | sh

AI review by kimi-k2.7-code on 2026-10-28. Automated pattern scan on 2026-10-28. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

maritimeint compared with similar skills

All 4 of these similar skills score higher than maritimeint; compare them before choosing.

SkillScoreStarsUpdatedFormat
maritimeint (this skill)by cognis-digital76346d agoMCP Server
Agent-Reachby Panniantong100107.8k1d agoCLAUDE.md
headroomby headroomlabs-ai10078.6ktodayCLAUDE.md
CowAgentby zhayujie10047.8ktodayCLAUDE.md
Scraplingby D4Vinci10092.4ktodayMCP Server

Frequently asked questions

How do I install maritimeint?
Run claude mcp add cognis-digital -- npx -y github:cognis-digital/maritimeint. The install tabs above show the steps for each supported agent.
Which AI agents does maritimeint work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is maritimeint safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (1 minor note below). An AI review of the same text found nothing harmful. It declares no license and scores 75/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is maritimeint still maintained?
The repository was last updated about 2 months ago, so maritimeint is actively maintained.

<a name="top"></a>

<div align="center"> <img src="https://capsule-render.vercel.app/api?type=rect&color=0:6b46c1,100:2b6cb0&height=120&section=header&text=MARITIMEINT&fontSize=48&fontColor=ffffff&fontAlignY=58" width="100%" alt="MARITIMEINT"/>

MARITIMEINT

AIS vessel tracking & sanctions-evasion anomaly detection

<img src="https://readme-typing-svg.demolab.com?font=Fira+Code&size=18&duration=3500&pause=1000&color=6B46C1&center=true&vCenter=true&width=720&lines=AIS+vessel+tracking++sanctionsevasion+anomaly+detection;Self-hostable+%C2%B7+MCP-native+%C2%B7+CI-ready+%C2%B7+polyglot" width="720"/>

PyPI CI License: COCL 1.0 Suite

OSINT / SIGINT — open-source intelligence collection and correlation.

</div>
pip install cognis-maritimeint
maritimeint locate demos/ais_sample.json   # → prioritized grey-fleet watchlist in seconds

🆕 New in v0.9 — track-interaction & vessel-behaviour intelligence

| | What changed | Try it | |---|---|---| | 🎯 | CPA / TCPA close-quarters — Closest Point of Approach + Time to CPA for every vessel pair; flags converging tracks projected to pass inside a danger radius (collision avoidance / standoff-perimeter breach). Pure relative-motion math — separation only, never an intercept | maritimeint close-quarters ais.json | | 🛰️ | Shadowing — one vessel persistently trailing another at a held standoff on a matched course (surveillance / interdiction / escort-precursor signature — distinct from a rendezvous) | maritimeint shadowing ais.json | | 🚢 | Convoy / co-movement — clusters of vessels moving together (tight grouping + matched heading & speed across epochs): escort groups & shepherded grey-fleet flotillas single-vessel detection misses | maritimeint convoy ais.json | | 🆘 | Drift / not-under-command — near-zero speed with erratic heading swing → disabled / dragging / possible-distress safety early-warning | maritimeint drift ais.json | | 🧩 | encounters mode + folded into analyze — all four run in one pass, score the risk ranking, and export to GeoJSON/KML/STIX/CSV unchanged | maritimeint encounters ais.json |

All four are pure-stdlib, additive layers — see the encounters guide and demos/05-encounters.

New in v0.8 — spatial intelligence, dark-STS & live 2026 sources

| | What changed | Try it | |---|---|---| | 🗺️ | Zone intelligence (geofencing) — define EEZs, sanctioned ports & exclusion / war-risk zones as GeoJSON; every finding is tagged with where it happened | maritimeint zones ais.json --zones zones.geojson | | 🌑 | Dark-rendezvous correlation — the real dark-STS move: one tanker kills AIS while another loiters at the spot (the case plain rendezvous can't see) | maritimeint dark-rendezvous ais.json | | 📡 | GPS spoofing & jamming — flags circling spoof tracks and jamming hotspots where many vessels snap to one synthetic position | maritimeint gps ais.json | | ⚓ | Port-call sequencing — reconstructs each vessel's itinerary and flags sanctioned-port legs | maritimeint port-calls ais.json --itinerary | | 🔴 | 3× more sources + real-time scraping — source catalog tripled with live 2026 feeds, plus a new keyless livesearch module that pulls current OSINT at runtime (Google News · RSS/Atom · DuckDuckGo), no API keys | python -m livesearch "sanctioned tanker" --when 7d |

All four detectors are pure-stdlib, additive layers folded into analyze / locate — see the v0.8 walkthrough and demos/04-dark-sts-zones.

<!-- cognis:example:start -->

Watch the walkthrough

A full narrated tour — setup, the tool in action, and every demo scenario:

Watch the maritimeint walkthrough

▶ Watch the walkthrough (MP4)

🔎 Example output

Real, reproducible output from the tool — runs offline:

$ maritimeint --version
maritimeint 0.9.0
$ maritimeint --help
usage: maritimeint [-h] [--version] [--format {table,json}]
                   {analyze,gaps,jumps,loiter,spoof,rendezvous,dark-rendezvous,gps,close-quarters,shadowing,convoy,drift,encounters,zones,port-calls,locate,vision,export,menu,addins,import-ofac,feeds,import-sanctions,fetch-ais} ...

AIS vessel tracking & sanctions-evasion anomaly detection.

positional arguments:
  {analyze,gaps,jumps,loiter,spoof,rendezvous,dark-rendezvous,gps,close-quarters,shadowing,convoy,drift,encounters,zones,port-calls,locate,vision,export,menu,addins,import-ofac,feeds,import-sanctions,fetch-ais}
    analyze             run full detector suite + risk ranking
    gaps                detect AIS reporting gaps (going dark)
    jumps               detect implausible position jumps
    loiter              detect loitering / STS staging
    spoof               detect spoofing / identity conflicts
    rendezvous          detect vessel-to-vessel meetings
    dark-rendezvous     correlate a vessel going dark with another loitering
                        at the spot
    gps                 detect GPS spoofing (circling) / jamming hotspots
    close-quarters      CPA/TCPA: vessel pairs projected to pass dangerously
                        close
    shadowing           detect one vessel persistently trailing another at
                        standoff
    convoy              detect groups of vessels moving together (co-movement)
    drift               detect adrift / not-under-command vessels
                        (safety/distress)
    encounters          run the full track-interaction suite (CPA + shadow +
                        convoy + drift)
    zones               detect zone/geofence entries, exits and dwell
    port-calls          infer port calls + sequence itineraries (risk-tagged)
   

Blocks above are real maritimeint output — reproduce them from a clone.

Sample result format (illustrative values — run on your own data for real findings):

{
"analyze": [
  {
    "id": "123456",
    "risk_rank": 3,
    "events": [
      {
        "type": "gaps",
        "start": "2022-01-01T00:00:00Z",
        "end": "2022-01-02T12:00:00Z"
      },
      {
        "type": "jumps",
        "start": "2022-01-03T14:00:00Z",
        "end": "2022-01-04T16:00:00Z"
      }
    ]
  }
]
}
<!-- cognis:example:end -->

Contents

<a name="why"></a>

Why maritimeint?

AIS vessel tracking & sanctions-evasion anomaly detection — without standing up heavyweight infrastructure.

maritimeint is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.

<div align="right"><a href="#top">↑ back to top</a></div>

<a name="features"></a>

Features

  • ✅ Parse Messages
  • ✅ Load Messages
  • ✅ Haversine Nm
  • ✅ Detect Gaps
  • ✅ Detect Speed Jumps
  • ✅ Detect Loitering
  • ✅ Detect Spoofing
  • ✅ Detect Rendezvous (ship-to-ship transfer signature)
  • ✅ CPA / TCPA close-quarters v0.9 — Closest Point of Approach + Time to CPA per vessel pair; flags converging tracks projected to pass inside a danger radius (the bridge collision-avoidance primitive, applied to AIS history for safety & force-protection standoff monitoring — separation only, no intercept/targeting)
  • ✅ Shadowing v0.9 — one vessel persistently trailing another at a held standoff on a matched course; reports leader/follower roles (surveillance / interdiction / escort-precursor signature, distinct from a rendezvous)
  • ✅ Convoy / co-movement clustering v0.9 — groups of vessels moving as one formation (proximity + matched heading & speed across epochs): escort groups & shepherded flotillas single-vessel detection treats as unrelated
  • ✅ Drift / not-under-command v0.9 — near-zero speed with erratic heading swing → disabled / anchor-dragging / possible-distress safety early-warning
  • ✅ encounters mode v0.9 — runs all four interaction/behaviour detectors in one pass; also folded into analyze so they score the risk ranking and flow through every exporter (guide)
  • ✅ Dark-rendezvous correlation v0.8 — one vessel goes dark while another loiters at the vanish point (the dark-STS signature rendezvous misses, because only one party is broadcasting)
  • ✅ Zone intelligence / geofencing v0.8 — GeoJSON or native polygons + great-circle "circle" zones (EEZs · sanctioned ports · exclusion / war-risk); entry/exit/dwell events + every positional finding tagged with its zone
  • ✅ GPS spoofing & jamming v0.8 — circle_spoof (a track populating the whole compass around a tight centroid) + gps_jamming (many distinct MMSIs pinned to one synthetic position)
  • ✅ Port-call sequencing v0.8 — dwell-based port calls from a built-in (or custom) registry, sequenced into per-vessel itineraries with sanctioned-port legs flagged
  • ✅ Live 2026 sources + real-time scraping v0.8 — livesearch.py: keyless, stdlib, real-time web-search + RSS/Atom ingestion (web_search · fetch_feed · ddg_search · harvest); the SOURCES.md catalog now carries 3× the feeds, queries & APIs
  • ✅ Native intel export v0.9 — turn any analysis into GeoJSON (Leaflet/Mapbox/QGIS/kepler.gl), KML (Google Earth / marine charts), STIX 2.1 bundle (threat-intel platforms) or CSV — zero dependencies: maritimeint export ais.json --to geojson
  • ✅ LocateAnything watchlist — one call → prioritized, explained grey-fleet watchlist (HIGH/MEDIUM/LOW + plain-language reasons)
  • ✅ Sanctions cross-reference — match tracked vessels to an OFAC/EU/OFSI-style list by MMSI / IMO / name
  • ✅ Composable AI add-ins — optional vision (imagery triage) + reasoning (narrative assessment) that stack onto the stdlib core, via the Cognis fleet / edgemesh; hardware/availability-gated (off if no backend)
  • ✅ Multi-level interactive menu (maritimeint menu)
  • ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
  • ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Grey-fleet watchlist + AI add-ins

maritimeint locate demos/ais_sample.json --sanctions demos/sanctions_sample.json
#  [HIGH ] 210111000 NEPTUNE STAR [SANCTIONED]  score=12
#        - ON SANCTIONS LIST (...)   - AIS gap 9h (going dark)
#        - rendezvous 90min, 0.008nm (possible ship-to-ship transfer)
maritimeint addins                 # which AI add-ins are reachable right now
maritimeint locate <ais.json> --ai # augment with the reasoning model if a backend is up
maritimeint menu                   # interactive, multi-level

# point the add-ins at a LIVE edgemesh gateway (or any OpenAI-compatible /v1

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategorySecurity
Updated1mo ago
Forks0

Languages

Python

Trust signals

75/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium2 low