Save a property to your Booking.com wishlist/favorites. Requires being logged in.
AI agents use booking_save_property to create or update resources in MCP Booking — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Booking environment.
Saving a property to a wishlist creates or updates data (adds an item to a list) without irreversible consequences. The operation is reversible (the user can remove items from the wishlist), making it a Write rather than Destructive action.
From the tool's definition Tool description states 'Save a property to your Booking.com wishlist/favorites' — this modifies user account state by adding an entry to a personal list, which is a reversible write operation.
Attacks that exploit this kind of access
Save a property to your Booking.com wishlist/favorites. Requires being logged in. It is categorised as a Write tool in the MCP Booking MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Booking MCP server in PolicyLayer and add a rule for booking_save_property: 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 Booking. Nothing to install.
booking_save_property 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 booking_save_property 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 booking_save_property. 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.
booking_save_property is provided by the MCP Booking MCP server (markswendsen-code/mcp-booking). 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 →