Search for airport codes by name or city.
AI agents call airport_search to retrieve information from Flight Planner MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves airport information (codes) based on search criteria. It performs a lookup operation without creating, modifying, deleting, or executing any actions. The blast radius of misuse is minimal—an AI agent could retrieve incorrect airport codes, but this is information-only and reversible in downstream planning steps.
From the tool's definition Tool name is 'airport_search' and description states it 'Search for airport codes by name or city' — a pure query operation with no side effects.
Documented attack patterns abuse exactly the kind of access airport_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Flight Planner MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for airport_search:
{
"version": "1",
"default": "deny",
"tools": {
"airport_search": {}
}
}airport_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for airport codes by name or city. It is categorised as a Read tool in the Flight Planner MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Flight Planner MCP Server MCP server in PolicyLayer and add a rule for airport_search: 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 Flight Planner MCP Server. Nothing to install.
airport_search 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 airport_search 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 airport_search. 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.
airport_search is provided by the Flight Planner MCP Server MCP server (salamentic/google-flights-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Flight Planner MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Flight Planner MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.