https://www.kiwi.com

Executes flight searches across Kiwi.com's aggregated inventory using structured query parameters (origin, destination, dates, passenger count, cabin class). Implements server-side filtering and ranking logic that queries live airline APIs and metasearch partners, returning paginated results with pricing, duration, stops, and availability status. The MCP protocol wraps these queries as tool calls, allowing AI assistants to invoke searches with natural language interpretation translated to structured parameters.

Converts search results into bookable reservations by accepting passenger details (names, contact info, payment method) and submitting them through Kiwi.com's booking engine. Implements PCI-compliant payment processing (likely delegated to third-party processor) and returns booking confirmation with reference number, itinerary details, and receipt. The MCP server abstracts away payment gateway complexity, presenting a single 'book_flight' tool that handles multi-step checkout flows internally.

Retrieves, modifies, and cancels existing bookings using booking reference and passenger details as lookup keys. Implements state queries (fetch_booking) that return current itinerary, seat assignments, and ancillary services, plus mutation operations (modify_booking, cancel_booking) that interact with Kiwi.com's reservation system and potentially trigger airline APIs for seat changes or cancellations. MCP server likely maintains session context to avoid re-authentication for sequential operations on the same booking.

Enables AI assistants to set up price-watch rules on flight routes, returning notifications when prices drop below specified thresholds or when new cheaper options appear. Likely implemented via background job scheduling on Kiwi.com's servers that periodically re-queries the specified route and compares against baseline prices, triggering webhook callbacks or email notifications to the MCP client. The MCP tool exposes create_price_alert, list_alerts, and delete_alert operations that manage these monitoring rules.

Constructs complex multi-leg trips (e.g., NYC → London → Paris → NYC) by chaining individual flight searches and applying optimization logic (minimize total duration, minimize total cost, balance layover times). The MCP server likely exposes a high-level 'plan_trip' tool that accepts a list of waypoints and constraints, then internally decomposes into sequential searches and ranks results by user-specified criteria. May implement dynamic programming or greedy algorithms to find optimal routing across multiple segments.

Interprets free-form natural language travel requests (e.g., 'I want to fly from New York to Paris next summer for 2 weeks') and extracts structured parameters (origin, destination, dates, passenger count) that feed into flight search tools. Likely implemented via prompt engineering or fine-tuned language model on the MCP client side (Claude or other AI assistant), but the MCP server may provide schema definitions and validation hints that guide the parsing. The server may also expose a 'validate_parameters' tool that checks if extracted parameters are valid (e.g., airport codes exist, dates are in future).