AI agents call maritime.port to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval from a static maritime reference database. The 'look up' verb indicates a read-only query operation with no side effects, state changes, or command execution. While hosted on a pay-per-call platform, the tool itself does not execute external operations, delete data, or create financial obligations beyond standard API usage fees.
From the tool's definition Tool description states 'Look up world ports and terminals' — a query/retrieval operation with no modification or execution. The NGA World Port Index is a public reference database.
Attacks that exploit this kind of access
Look up world ports and terminals in the NGA World Port Index (Pub 150, ~2,950 ports) by port name (partial) and/or country (full name, e.g. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for maritime.port: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
maritime.port is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the maritime.port rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for maritime.port. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
maritime.port is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →