destinations_from
All airports reachable nonstop from a given origin, with the service kinds (scheduled, seasonal, charter, suspended, ...) per destination. Optionally filter by kind and include the operating airlines. Seasonal and charter service carries no operating dates; treat as unverified for specific travel...
This record as markdown: /tools/com-flywhereto-mcp/destinations-from.md
What destinations_from does on Fly Where To?
AI agents call destinations_from to retrieve information from Fly Where To? without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
kind | string | — | Only destinations with at least one route of this service kind |
origin | string | Yes | Three-letter IATA airport code, e.g. "IST" |
include_airlines | boolean | — | Also list the operating airlines per destination (larger response) |
Parameters from the server's own tool schema.
Why destinations_from is rated Low
Even though destinations_from only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs destinations_from safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Fly Where To?, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For destinations_from, this is the rule to start with:
destinations_from is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Fly Where To?, apply this rule, and every destinations_from call is checked against it from then on.
Questions about destinations_from
All airports reachable nonstop from a given origin, with the service kinds (scheduled, seasonal, charter, suspended, ...) per destination. Optionally filter by kind and include the operating airlines. Seasonal and charter service carries no operating dates; treat as unverified for specific travel dates. It is categorised as a Read tool in the Fly Where To? MCP Server, which means it retrieves data without modifying state.
destinations_from accepts 3 parameters: kind, origin, include_airlines. Required: origin. The full parameter table on this page comes from the server's own tool schema.
Register the Fly Where To? MCP server in PolicyLayer and add a rule for destinations_from: 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 Fly Where To?. Nothing to install.
destinations_from 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 destinations_from 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 destinations_from. 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.
destinations_from is provided by the Fly Where To? MCP server (https://flywhereto.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Fly Where To?, and thousands of servers like it.
This server
Across the catalogue