search_flights
AI agents call search_flights to retrieve information from Trip Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves flight information from Google Flights. It queries data to help users plan trips but does not create, modify, delete, or execute operations with side effects. The empty description and read-only nature of flight searches (no booking, purchasing, or cancellation capability in this tool) places it squarely in the Read category with low severity and high confidence.
From the tool's definition Tool name 'search_flights' combined with server description indicating 'live searches against Google Flights' and sibling tools like 'search_activities', 'search_events', and 'search_stays' all perform query/retrieval operations without modification.
Attacks that exploit this kind of access
search_flights. It is categorised as a Read tool in the Trip Search MCP Server, which means it retrieves data without modifying state.
Register the Trip Search MCP server in PolicyLayer and add a rule for search_flights: 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.
search_flights is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_flights 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 search_flights. 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.
search_flights 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 →