Search for airports by name or city to find the correct IATA code.
AI agents call list_airports to retrieve information from Duffel 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 (IATA codes) based on search criteria. It is a read-only lookup function that returns reference data without creating, modifying, deleting, or executing any operations. The lack of side effects and purely informational nature places it firmly in the Read category with low severity.
From the tool's definition Tool description states 'Search for airports by name or city to find the correct IATA code' — a pure lookup/query operation with no data modification or side effects.
Attacks that exploit this kind of access
Search for airports by name or city to find the correct IATA code. It is categorised as a Read tool in the Duffel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Duffel MCP Server MCP server in PolicyLayer and add a rule for list_airports: 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 Duffel MCP Server. Nothing to install.
list_airports 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 list_airports 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 list_airports. 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.
list_airports is provided by the Duffel MCP Server MCP server (naren8642/duffel-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 →