Full record and prose for one named moorage, plus (for outstations) its club
AI agents call get_moorage to retrieve information from Outstations without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation on yacht-club outstation records. It fetches and returns moorage information (size limits, rafting rules, amenities, overnight-comfort ranking, and club affiliation) based on a name parameter. No data is created, modified, deleted, or acted upon; no external operations are triggered.
From the tool's definition Tool retrieves 'full record and prose for one named moorage' — a query operation that returns data about existing moorage records without modification, deletion, or execution of commands.
Attacks that exploit this kind of access
Full record and prose for one named moorage, plus (for outstations) its club. It is categorised as a Read tool in the Outstations MCP Server, which means it retrieves data without modifying state.
Register the Outstations MCP server in PolicyLayer and add a rule for get_moorage: 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 Outstations. Nothing to install.
get_moorage 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 get_moorage 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 get_moorage. 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.
get_moorage is provided by the Outstations MCP server (sailingnaturali/outstations-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 →