AI agents use manage_booking to create or update resources in Mcp Turo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Turo environment.
This tool performs reversible write operations on booking records. While cancellation is somewhat destructive in intent, Turo's business model typically permits cancellations within windows (often with refunds), making it a Write rather than Destructive action.
From the tool's definition Tool enables "modify or cancel an existing Turo booking" — these are reversible modifications to booking state (cancellation can typically be reversed within cancellation policies).
Attacks that exploit this kind of access
View, modify, or cancel an existing Turo booking. Use action=. It is categorised as a Write tool in the Mcp Turo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Turo MCP server in PolicyLayer and add a rule for manage_booking: 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.
manage_booking is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the manage_booking 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 manage_booking. 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.
manage_booking 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 →