AI agents call get_incidents 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 retrieves real-time transit incident and advisory information from the WMATA system. It performs a query operation with no side effects—it does not create, modify, delete, or execute any actions. The blast radius of misuse is minimal; an AI could only retrieve incident data repeatedly, which poses no security, operational, or data integrity risk.
From the tool's definition Tool name 'get_incidents' and description 'Get current Metro rail incidents and service advisories' indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
Get current Metro rail incidents and service advisories. 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_incidents: 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_incidents 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_incidents 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_incidents. 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_incidents 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 →