Vessel Traffic MCP server
io.github.tools-mcp/vessel-traffic-mcp·v0.1.0·6 starsRead-only MCP server for vessel AIS, ship tracking, schedules, and BYOK maritime providers.
6 stars41 downloads/wk
Reviews
Write oneNobody has reviewed Vessel Traffic MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Vessel Traffic MCP tools (14)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
carrier_schedule_searchSearch carrier sailing schedules by origin/destination, carrier SCAC/name, cargo type, direct-only flag, and departure/arrival windows. Returns normalized schedules with upstream source metadata.
credential_profilesList BYOK credential profile labels, provider hints, declared field names, and status. Raw keys are never returned.
data_sourcesList available vessel data source adapters, coverage notes, auth mode, and caveats.
document_vessel_lookupExtract vessel signals (name, IMO/MMSI/callsign, voyage, ports, container numbers, dates) from B/L-style text and return ranked candidates.
port_callsReturn recent port-call events for a vessel by MMSI/IMO or for a UN/LOCODE port. Requires at least one filter.
provider_onboardingShow safe manual signup, API docs, credential env vars, configured status, and validation steps for provider access. Does not create accounts or issue credentials.
provider_statusList configured vessel data providers, auth state, feature support, quota hints, and caveats.
schedule_delay_predictCompare planned carrier schedule timestamps with estimated/actual timestamps and return an on-time, at-risk, delayed, or unknown heuristic.
vessel_areaReturn latest known positions for vessels inside a bounding box (latMin<=latMax, lonMin<=lonMax) with provider source metadata.
vessel_name_resolveResolve a messy vessel name (e.g. from B/L text) to ranked MMSI/IMO candidates with matched/missing signals and confidence.
vessel_positionReturn the latest known position for a vessel by MMSI or IMO with source, retrievedAt, observedAt, and freshness metadata.
vessel_scheduleReturn scheduled carrier port calls for a vessel by MMSI, IMO, vessel name, voyage number, or carrier SCAC with source metadata.
vessel_searchSearch vessels by MMSI, IMO, name, or callsign. Requires at least one identifier; returns normalized identities with provider source metadata.
vessel_trackReturn the recent track points for a vessel by MMSI or IMO, optionally bounded by ISO-8601 windowStart/windowEnd.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan66 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 5 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Vessel Traffic MCP compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 85% of 48,255 servers
- Tools
- 14
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 6
- more than 85% of 28,688 servers
- Downloads a week
- 41
- more than 33% of 12,191 servers with a package
What its tools let an agent do: 14 read
Install Vessel Traffic MCP in Claude Code, Cursor or VS Code
Runs npx -y @tools-mcp/vessel-traffic-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add vessel-traffic-mcp -- npx -y @tools-mcp/vessel-traffic-mcp
What the publisher says
From the Vessel Traffic MCP repository's README, as published. We do not edit it. Read it on GitHub
Vessel Traffic MCP
English | 한국어 | 日本語 | 中文
Vessel tracking and shipping schedules for AI agents.
Vessel Traffic MCP is a read-only Model Context Protocol (MCP) server for vessel identity lookup, AIS-style positions, tracks, port calls, carrier schedules, vessel schedules, and delay heuristics. It gives Claude, ChatGPT, Codex, MCP Inspector, and other MCP clients one normalized maritime-data tool surface.
Use it when an agent needs to:
- search/fetch vessel context through generic connector-style MCP tools;
- resolve a vessel from a name, MMSI, IMO, callsign, or bill-of-lading text;
- ask where a vessel is, where it has been, or which vessels are in an area;
- search container-shipping schedules by port pair or vessel;
- return the original provider and source URL with every live/public result;
- test maritime workflows safely before buying paid AIS or schedule APIs.
The project does not bypass provider terms, paywalls, CAPTCHA, or access controls. Commercial providers are Bring Your Own Key (BYOK), the default test path is fixture-only, and this is not a navigation product.
Open source under the MIT license. Pre-1.0; APIs and tool surfaces may change.
Contents
- Install In An MCP Client
- Agent Discovery Page
- What It Exposes
- Provider Model
- Responsible Use And Third-Party Rights
- Help Spread
- From Source
- Remote HTTP Setup
- Current Distribution
- Star History
- Shared Reference
Install In An MCP Client
For Claude Desktop, Claude Code, Codex CLI, Cursor, VS Code, or any stdio MCP client, use the npm package:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Vessel Traffic MCP: common questions
- Is Vessel Traffic MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Vessel Traffic MCP safety report
- How do I install Vessel Traffic MCP?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Vessel Traffic MCP need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is Vessel Traffic MCP maintained?
- The last commit was 43 days ago (2026-09-22). The latest release is v0.1.0.
- How does Vessel Traffic MCP compare with other MCP servers?
- safety score 91/100 (higher than 85% of 48,255 servers); tools 14 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.