AI agents call search_vehicles to retrieve information from Mcp Hertz without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about vehicle availability and pricing from the Hertz system. It performs no creation, modification, deletion, or execution of commands. No financial transactions or state changes occur. This is a straightforward Read operation with minimal risk even if misused by an agent.
From the tool's definition Tool description states it "Search[es] for available vehicles" and "Returns a list of available cars with pricing." These are query/retrieval operations with no side effects. The name 'search_vehicles' and verb 'Search' confirm retrieval intent.
Attacks that exploit this kind of access
Search for available vehicles at Hertz for specific dates, locations, and preferences. Returns a list of available cars with pricing. It is categorised as a Read tool in the Mcp Hertz MCP Server, which means it retrieves data without modifying state.
Register the Mcp Hertz MCP server in PolicyLayer and add a rule for search_vehicles: 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 Mcp Hertz. Nothing to install.
search_vehicles 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_vehicles 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_vehicles. 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_vehicles is provided by the Mcp Hertz MCP server (markswendsen-code/mcp-hertz). 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 →