AI agents call get_station_predictions 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 performs a query operation returning transit information to the user. It has no side effects, cannot modify system state, execute commands, delete data, or commit financial transactions. The maximum blast radius from misuse is providing inaccurate transit information to an AI agent, which could result in user inconvenience but no irreversible harm or security breach.
From the tool's definition Tool retrieves real-time train arrival predictions with no capability to modify, delete, or execute operations.
Attacks that exploit this kind of access
Get real-time train arrival predictions for a Metro station. 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_station_predictions: 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_station_predictions 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_station_predictions 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_station_predictions. 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_station_predictions 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 →