AI agents call search_cars to retrieve information from Mcp Turo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries rental car availability data from the Turo platform. It produces no side effects—no bookings are made, no data is modified, and no financial transactions occur. It is a straightforward search/query function that fits the Read category definition of retrieval without side effects.
From the tool's definition Tool description states it 'Search[es] for available rental cars' with filters. The verb 'search' and the read-only nature of querying listings without side effects indicates a retrieval operation.
Attacks that exploit this kind of access
Search for available rental cars on Turo by location, dates, and optional filters such as price range and vehicle type. It is categorised as a Read tool in the Mcp Turo MCP Server, which means it retrieves data without modifying state.
Register the Mcp Turo MCP server in PolicyLayer and add a rule for search_cars: 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 Turo. Nothing to install.
search_cars 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_cars 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_cars. 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_cars is provided by the Mcp Turo MCP server (markswendsen-code/mcp-turo). 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 →