AI agents call get_stations_by_line to retrieve information from Metro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely queries and returns a list of stations that serve a particular Metro line. It has no side effects, cannot modify data, execute commands, or affect system state. The information retrieved is public transit infrastructure data that users would expect to access. The blast radius of misuse is minimal—at worst, an agent could retrieve transit data repeatedly, but this causes no harm to systems or data.
From the tool's definition Tool retrieves station information for a specific Metro line ('Get all stations on a specific Metro line'). The verb 'Get' and the context of querying static transit data indicates a read-only operation with no modification or execution capability.
Attacks that exploit this kind of access
Get all stations on a specific Metro line. It is categorised as a Read tool in the Metro MCP MCP Server, which means it retrieves data without modifying state.
Register the Metro MCP server in PolicyLayer and add a rule for get_stations_by_line: 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 Metro MCP. Nothing to install.
get_stations_by_line 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_stations_by_line 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_stations_by_line. 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_stations_by_line is provided by the Metro MCP server (nathanielnoyd/metro-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 →