AI agents use book_flight to commit financial operations through LetsFG — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Booking a flight creates a real reservation (PNR) with financial consequences: payment is charged and a legal travel contract is formed. This is a Financial action with critical severity because an AI agent misusing this tool could make irreversible, costly bookings on behalf of users.
From the tool's definition "Book an unlocked flight — creates real airline reservation with PNR" — commits a real airline booking and financial obligation
Attacks that exploit this kind of access
Book an unlocked flight — creates real airline reservation with PNR (step 3 of 3). Developer API only.\n\n. It is categorised as a Financial tool in the LetsFG MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the LetsFG MCP server in PolicyLayer and add a rule for book_flight: 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 LetsFG. Nothing to install.
book_flight 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 book_flight 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 book_flight. 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.
book_flight is provided by the LetsFG MCP server (letsfg/letsfg). 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 →