AI agents use ihg_book_room to commit financial operations through Mcp Ihg — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Booking a hotel room creates a financial commitment and may charge a credit card. This is a Financial category action with critical severity because an AI agent misusing this tool could create unwanted reservations and incur real monetary costs that may be difficult to reverse, especially for non-refundable rates.
From the tool's definition "Book a hotel room" and "Will complete the full booking flow" — this commits a financial obligation (hotel reservation charge) on behalf of the user.
Attacks that exploit this kind of access
Book a hotel room at an IHG property. Requires login. Will complete the full booking flow. It is categorised as a Financial tool in the Mcp Ihg MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Ihg MCP server in PolicyLayer and add a rule for ihg_book_room: 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 Ihg. Nothing to install.
ihg_book_room 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 ihg_book_room 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 ihg_book_room. 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.
ihg_book_room is provided by the Mcp Ihg MCP server (markswendsen-code/mcp-ihg). 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 →