Rank overnight-capable moorage by comfort against a forecast (same scoring
AI agents call rank_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 is a retrieval and evaluation tool that queries moorage data to produce ranked results. It performs no modifications, deletions, or external operations. The only capability is reading existing records and applying a ranking algorithm to present them in different orders.
From the tool's definition Tool ranks existing moorage records by comfort metrics against forecasts. The description indicates it scores/evaluates data rather than modifying it. The 'rank' operation is a read/query pattern that retrieves and sorts information without side effects.
Attacks that exploit this kind of access
Rank overnight-capable moorage by comfort against a forecast (same scoring. 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 rank_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.
rank_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 rank_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 rank_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.
rank_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 →