Get a
AI agents use booking_book to commit financial operations through MCP Booking — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Booking a hotel room creates a financial commitment (payment or hold) on behalf of the user. Even though the description is truncated and uninformative ('Get a'), the tool name combined with server context (Booking.com hotel booking via browser automation) strongly implies this tool completes a reservation, which is a financial action. Financial is the most severe applicable category.
From the tool's definition Tool name 'booking_book' on a server that 'book rooms on Booking.com' — booking a room commits a financial obligation; sibling tools include 'booking_cancel_reservation' confirming real reservation lifecycle management
Attacks that exploit this kind of access
Get a. It is categorised as a Financial tool in the MCP Booking MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the MCP Booking MCP server in PolicyLayer and add a rule for booking_book: 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_book is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the booking_book 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_book. 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_book 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 →