watch_flight_price
AI agents use watch_flight_price to create or update resources in Trip Search — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trip Search environment.
Based on the name and sibling tool 'cancel_watch'/'list_active_watches', this tool likely creates a price watch/alert for a flight, which is a reversible write operation (creating a watch record). The existence of 'cancel_watch' implies watches can be undone. Confidence is low due to empty description, but the pattern suggests a Write action rather than anything more severe.
From the tool's definition Tool name 'watch_flight_price'; description is empty and uninformative.
Attacks that exploit this kind of access
watch_flight_price. It is categorised as a Write tool in the Trip Search MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trip Search MCP server in PolicyLayer and add a rule for watch_flight_price: 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 Trip Search. Nothing to install.
watch_flight_price 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 watch_flight_price 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 watch_flight_price. 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.
watch_flight_price is provided by the Trip Search MCP server (nanwer/trip-search-mcp). 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 →