Find Metlink stops by partial name match.
AI agents call search_stops to retrieve information from Wellington Transport Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against a public transport database. It retrieves matching stop records based on a search term but does not create, modify, delete, or execute any code. The data being queried is public transport infrastructure information (stop locations/names), not sensitive or financial in nature.
From the tool's definition Tool name 'search_stops' and description 'Find Metlink stops by partial name match' indicate a query operation that retrieves public transport stop information without modifying data.
Attacks that exploit this kind of access
Find Metlink stops by partial name match. It is categorised as a Read tool in the Wellington Transport Assistant MCP Server, which means it retrieves data without modifying state.
Register the Wellington Transport Assistant MCP server in PolicyLayer and add a rule for search_stops: 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 Wellington Transport Assistant. Nothing to install.
search_stops 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_stops 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_stops. 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_stops is provided by the Wellington Transport Assistant MCP server (sdhilip200/metlink-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 →