Select a seat on a booking. If the seat has a price, this charges the stored payment method — check
AI agents use SELECT_FLIGHT_SEAT to commit financial operations through Travel Agent MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool can trigger a financial charge against the user's stored payment method when selecting a priced seat. This makes it a Financial category tool. Severity is high because an AI agent could inadvertently select expensive seats and charge the user without explicit confirmation.
From the tool's definition 'If the seat has a price, this charges the stored payment method'
Attacks that exploit this kind of access
Select a seat on a booking. If the seat has a price, this charges the stored payment method — check. It is categorised as a Financial tool in the Travel Agent MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Travel Agent MCP Server MCP server in PolicyLayer and add a rule for SELECT_FLIGHT_SEAT: 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 Travel Agent MCP Server. Nothing to install.
SELECT_FLIGHT_SEAT 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 SELECT_FLIGHT_SEAT 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 SELECT_FLIGHT_SEAT. 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.
SELECT_FLIGHT_SEAT is provided by the Travel Agent MCP Server MCP server (nxgnosis/travelagentmcp). 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 →