search_stations
AI agents call search_stations to retrieve information from NS Travel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries station data with no side effects. The name and server context strongly indicate a search/lookup operation. Lack of description lowers confidence slightly, but the pattern of sibling tools and the 'search' verb confirm Read category. Severity is low because querying public transit station information has minimal blast radius even if misused.
From the tool's definition Tool name is 'search_stations' and server context indicates it provides 'station search' functionality. No description provided, but the name and sibling tools (check_disruptions, get_live_departures, plan_journey) are all read-only query operations for…
Attacks that exploit this kind of access
search_stations. It is categorised as a Read tool in the NS Travel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NS Travel MCP Server MCP server in PolicyLayer and add a rule for search_stations: 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 NS Travel MCP Server. Nothing to install.
search_stations 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 search_stations 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 search_stations. 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.
search_stations is provided by the NS Travel MCP Server MCP server (lauragift21/ns-travel-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 →