whentofly
Server Details
whentofly: flexible-date economy/business flight search + price-level context for AI agents
- Status
- Healthy
- Uptime
- 99.0% over 42 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- dimabalony/whentofly-mcp
- GitHub Stars
- 3
- Server Listing
- whentofly
TDQS
Scored across 2 tools
The two tools have sharply distinct roles: search_locations resolves place names/codes into typed values, while search_flights consumes those values to find fares. No overlap or ambiguous selection between them.
Both tools follow the same verb_noun pattern (search_flights, search_locations). The convention is uniform and intuitive.
Two tools is on the lean side, but each earns its place: one core search operation and one supporting location resolver. The narrow 'when to fly' purpose makes the count reasonable, though slightly below the typical 3-15 range.
The core workflow of location resolution plus flexible multi-month flight search is fully covered. Minor gaps exist (e.g., no explicit one-way or exact-date operation), but the flexible-window design accommodates most travel needs without dead ends.
Available Tools
2 toolssearch_flightsARead-onlyIdempotentInspect
Find the cheapest round-trip across a FLEXIBLE multi-month date window with a min/max trip length — e.g. "10–15 days, anytime Sep–Nov". Search a broad date window rather than requiring the traveler to choose exact dates first. First call the search_locations MCP tool for city or airport names, then pass each returned airport:AAA or city:AAA value unchanged as origin/destination (explicit legacy IATA codes remain supported). Dates are OPTIONAL: add an earliest/latest window when the traveler has one, or omit them (or give just one side) and a sensible default window is searched — metadata.window_defaulted says so and query echoes the window used, so a dateless call always returns flights instead of an error. Add min/max trip duration; get back a ranked list of the cheapest fares (with booking links) plus a price verdict — an honest read of whether the cheapest fare is low, typical, or high versus the route's usual price, or unknown when we lack a usable typical-price band (a price-level read, not a buy-now-or-wait timing prediction). Non-economy requests may return action-bound Google Flights seller quotes or separate route-price evidence in metadata.route_price_check. For a specific route, set checked_bags=1 when the traveler needs one checked bag, then inspect each result's price_basis; anywhere discovery does not support baggage pricing. Checked-bag searches still run seller enrichment but set the fare-only verdict and metadata.route_price_check to null; verify=full does not override that boundary. Use it for any flight question where the dates are flexible, unknown, or the user wants the cheapest time to fly. If a window comes back thin or cannot fit the return, the search widens it one step itself and reports that in metadata.hints — no second call needed. A city:/airport: prefix that contradicts its code (city:CDG names an airport, airport:PAR names a city) is likewise searched as the identity the catalog does know, with a selector_corrected entry in metadata.hints naming the requested and used tokens. Dates already in the past get the same treatment: a window that only STARTS in the past is searched from today with a window_clamped entry in metadata.hints, and a window that has already ENDED is not searched at all — the results are empty and a window_in_past entry names a suggested window to ask for instead, so do not retry the same dates. If metadata.refresh_hint is present, this response shipped without something a repeat call can add: issue the same call again immediately (do not sleep or poll) and read refresh_hint.action for what will be included. If you can wait longer for that best-effort cross-check, set verify=full. It uses a longer ~35s budget, but never treats a different airline, itinerary, gate, or booking URL as verification of the displayed offer. Pass sellers=false when the traveler wants the price picture but is not booking through this answer: it skips the live seller-quote wave, so the ranked calendar fares, booking links and metadata.route_price_check still come back but metadata.seller_enrichment_status is skipped and no seller quote, seller-level baggage fee or direct seller action is resolved. Provider failure, unavailability, or a spend cap can still return only cached indicators; always inspect metadata.seller_enrichment_status (applied means complete date-pair coverage put Serp-derived seller data in results; complete means the selected plan and action resolution completed without such data entering results; partial means date-pair or direct-action coverage has gaps though valid seller data may still rank; skipped is reserved for response surfaces where enrichment does not apply) and metadata.seller_enrichment_coverage. That object reports the theoretical query-valid date pairs and how many were targeted/searched; it is not exhaustive provider inventory. Default requests target at most three pairs, while explicit verify=full targets at most seven with bounded longer budgets. Inspect metadata.freshness, and metadata.route_price_check.
| Name | Required | Description | Default |
|---|---|---|---|
| ch | No | Acquisition channel tag (e.g. web, mcp, a campaign name) for first-party analytics. Durable booking links retain the validated Travelpayouts marker for commission but do not trust opaque shortlinks solely to carry provider-dashboard sub_id attribution. Defaults to 'direct'; reduced to a bounded registered channel. | direct |
| to | No | Destination location: a legacy code, airport:AAA, or city:AAA. Pass `anywhere` (or omit) to get the cheapest destinations from the origin instead of a specific route. | |
| from | Yes | Origin location. Use a legacy 3-letter code (SHA), an exact airport (airport:SHA), or an all-airports city (city:SHA). Required for every search, including to=anywhere. | |
| cabin | No | Cabin class: economy (default), premium_economy, business, or first. The Travelpayouts calendar covers economy; Google Flights may additionally return action-bound seller quotes for the requested cabin. Actionless evidence remains in metadata.route_price_check. | economy |
| top_n | No | Maximum number of results to return, sorted cheapest-first. Specific routes allow up to 50; anywhere mode returns at most 12. | |
| latest | No | Latest acceptable return date for round-trip, or latest acceptable departure for one-way (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Optional: omit it and it is derived from `earliest` (or from the default window when both are omitted). A window ending before today is not searched; the response is empty with a `window_in_past` hint. Ignored in anywhere mode. | |
| verify | No | How hard to cross-check the top result's route, dates, and cabin against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget and widen the request-local seller/date sample from at most three pairs to at most seven (set it when you can wait, e.g. an autonomous agent). The six-hour base and its cache key do not change. This does not verify the displayed airline, itinerary, gate, or booking URL; inspect `metadata.route_price_check` separately. Checked-bag searches keep this fare-only route check and verdict null even when verify=true or verify=full; seller-level baggage enrichment still runs. Displayed Travelpayouts fares remain explicitly labeled cached indicators. No-op unless a SerpApi key is configured. | false |
| one_way | No | If true, search one-way flights; return_date and duration_days will be null. | |
| sellers | No | Whether to run the live seller-quote wave (Google Flights `booking_options`) for this request. Default `true`: unchanged behavior — the bounded frontier resolves seller prices, baggage basis, and the executable booking action. Set `sellers=false` to ask for the ranked fare calendar and the route-level price check ONLY: the response then carries `metadata.seller_enrichment_status="skipped"`, results keep their Travelpayouts-grounded prices and durable booking links, and no seller quote, seller-level baggage fee, or direct seller action is resolved. It exists for callers that want the price picture cheaply and do not intend to book — our own curve-seeding crons use it — because the seller wave is where a search's provider spend actually goes (about seven of its ~eight calls). Non-economy cabins have no calendar source, so `sellers=false` there leaves `metadata.route_price_check` as the only priced evidence and `results` may be empty. | |
| currency | No | Result currency, 3-letter ISO code UPPERCASE. | USD |
| earliest | No | Earliest acceptable departure date (ISO YYYY-MM-DD). Optional: omit it and a default window is searched, with the applied window echoed in `query` and flagged by `metadata.window_defaulted`. A date already in the past is clamped to today and reported as `window_clamped` in `metadata.hints` — unless `latest` has passed too, in which case the whole window is declined rather than clamped (see `latest`). Ignored in anywhere mode. | |
| max_days | No | Maximum round-trip duration in days (return - departure); ignored for one-way and anywhere mode. | |
| min_days | No | Minimum round-trip duration in days (return - departure); ignored for one-way and anywhere mode. | |
| checked_bags | No | Checked bags requested for the current one-adult, specific-route search contract. Anywhere discovery rejects checked_bags=1. Set to 1 to add a seller's unambiguous first-checked-bag fee to the ranked customer price. Unknown fees remain labeled in results[].price_basis instead of being guessed. Seller enrichment still runs, but the fare-only verdict and route-price check remain null, including when verify=true or verify=full. | |
| max_transfers | No | Maximum number of transfers/layovers per leg. 0 = nonstop only, 1 = up to 1 stop, etc. Omit for no filter. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, and the description adds a large amount of non-obvious behavioral context: dateless calls default windows, past windows are clamped or declined, metadata.hints reports corrections, seller_enrichment_status has four distinct meanings, refresh_hint instructs an immediate repeat call, and checked-bag searches null the fare verdict even with verify=full. This goes far beyond what annotations or schema imply and gives agents actionable expectations. No contradiction with the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core use case and organized into related blocks, but it is very long and repeats details already present in the schema, such as sellers=false, verify=full, checked_bags, and non-economy behavior. Most sentences do carry operational information, but the same caveats appear both in the description and in parameter descriptions. It would be clearer as a shorter summary plus focused sections for metadata and edge cases.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description fully bears the burden of explaining return semantics. It covers ranked cheapest fares, booking links, price-verdict meaning, metadata flags like window_defaulted, refresh_hint, hints, seller_enrichment_status and seller_enrichment_coverage, past-window handling, and verify boundary behavior. An agent has enough information to invoke the tool correctly, interpret metadata, and know when to retry or not.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description still adds meaningful operational context beyond the schema: dates are optional and never cause an error, city:/airport: prefix contradictions are auto-corrected, sellers=false skips the spend-heavy seller wave, and verify=full changes time budget and coverage bounds. It does not systematically explain every parameter, so 4 rather than 5.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The opening sentence states a specific action and resource: 'Find the cheapest round-trip across a FLEXIBLE multi-month date window with a min/max trip length.' It clearly distinguishes the tool from a location-lookup tool by instructing the agent to call search_locations first, and it frames the search as flexible-date oriented rather than exact-date oriented. No ambiguity remains about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use it for any flight question where the dates are flexible, unknown, or the user wants the cheapest time to fly,' and it gives a concrete sequencing instruction to call search_locations first and pass returned values unchanged. It also covers when to set sellers=false, verify=full, and checked_bags=1. It does not name a fixed-date alternative or explicitly state when not to use it, so it stops just short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_locationsARead-onlyIdempotentInspect
Resolve a city or airport name or code before searching flights. Returns typed values such as city:SHA to search every catalog airport in Shanghai or airport:SHA for Hongqiao only. Pass the selected value unchanged to search_flights. Ask the traveler when multiple results are plausible.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Airport/city name or 3-letter code prefix. | |
| limit | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, non-destructive, and idempotent behavior. The description adds meaningful behavioral detail beyond annotations by explaining typed result values (e.g., city:SHA vs airport:SHA), catalog scope differences, and how to handle ambiguity. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences with no fluff. It front-loads the purpose, provides a concrete example of return values, and gives an integration instruction and ambiguity-handling rule, all of which earn their place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having no output schema, the description sufficiently explains the return format (typed values) and the meaning of those values. The main parameter q is well documented, and limit is covered by schema defaults. The tool is simple enough that this description is complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50%: q is described as 'Airport/city name or 3-letter code prefix' in schema, and the description enriches q with examples and the typed-prefix semantics. However, the limit parameter is not mentioned in the description, though schema covers its default and range.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Resolve' with a clear resource ('city or airport name or code') and explicitly frames it as a pre-step to searching flights, which strongly distinguishes it from the sibling search_flights tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly states 'before searching flights' and instructs to 'Pass the selected value unchanged to search_flights', giving a direct usage workflow. It also provides decision guidance by advising the agent to ask the traveler when multiple results are plausible.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
search_flights3 fields changed- changed
Input schema / properties / earliest / examplesPrevious value: -[ - "2026-09-26" -]New value: +[ + "2026-09-29" +] - changed
Input schema / properties / latest / examplesPrevious value: -[ - "2026-12-25" -]New value: +[ + "2026-12-28" +] - added
Input schema / properties / sellersAdded value: +{ + "default": true, + "description": "Whether to run the live seller-quote wave (Google Flights `booking_options`) for this request. Default `true`: unchanged behavior — the bounded frontier resolves seller prices, baggage basis, and the executable booking action. Set `sellers=false` to ask for the ranked fare calendar and the route-level price check ONLY: the response then carries `metadata.seller_enrichment_status=\"skipped\"`, results keep their Travelpayouts-grounded prices and durable booking links, and no seller quote, seller-level baggage fee, or direct seller action is resolved. It exists for callers that want the price picture cheaply and do not intend to book — our own curve-seeding crons use it — because the seller wave is where a search's provider spend actually goes (about seven of its ~eight calls). Non-economy cabins have no calendar source, so `sellers=false` there leaves `metadata.route_price_check` as the only priced evidence and `results` may be empty.", + "examples": [ + true, + false + ], + "title": "sellers", + "type": "boolean" +}
1 tool update
- Changed
search_flights4 fields changed- changed
Input schema / properties / earliest / descriptionPrevious value: -"Earliest acceptable departure date (ISO YYYY-MM-DD). Optional: omit it and a default window is searched, with the applied window echoed in `query` and flagged by `metadata.window_defaulted`. Ignored in anywhere mode."New value: +"Earliest acceptable departure date (ISO YYYY-MM-DD). Optional: omit it and a default window is searched, with the applied window echoed in `query` and flagged by `metadata.window_defaulted`. A date already in the past is clamped to today and reported as `window_clamped` in `metadata.hints` — unless `latest` has passed too, in which case the whole window is declined rather than clamped (see `latest`). Ignored in anywhere mode." - changed
Input schema / properties / earliest / examplesPrevious value: -[ - "2026-06-01" -]New value: +[ + "2026-09-26" +] - changed
Input schema / properties / latest / descriptionPrevious value: -"Latest acceptable return date for round-trip, or latest acceptable departure for one-way (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Optional: omit it and it is derived from `earliest` (or from the default window when both are omitted). Ignored in anywhere mode."New value: +"Latest acceptable return date for round-trip, or latest acceptable departure for one-way (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Optional: omit it and it is derived from `earliest` (or from the default window when both are omitted). A window ending before today is not searched; the response is empty with a `window_in_past` hint. Ignored in anywhere mode." - changed
Input schema / properties / latest / examplesPrevious value: -[ - "2026-08-31" -]New value: +[ + "2026-12-25" +]
1 tool update
- Changed
search_flights2 fields changed- changed
Input schema / properties / earliest / descriptionPrevious value: -"Earliest acceptable departure date (ISO YYYY-MM-DD). Required for a specific route; ignored in anywhere mode."New value: +"Earliest acceptable departure date (ISO YYYY-MM-DD). Optional: omit it and a default window is searched, with the applied window echoed in `query` and flagged by `metadata.window_defaulted`. Ignored in anywhere mode." - changed
Input schema / properties / latest / descriptionPrevious value: -"Latest acceptable return date for round-trip, or latest acceptable departure for one-way (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Required for a specific route; ignored in anywhere mode."New value: +"Latest acceptable return date for round-trip, or latest acceptable departure for one-way (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Optional: omit it and it is derived from `earliest` (or from the default window when both are omitted). Ignored in anywhere mode."
1 tool update
- Changed
search_flights2 fields changed- changed
Input schema / properties / ch / descriptionPrevious value: -"Acquisition channel tag (e.g. web, mcp, a campaign name). Encoded with the route into the affiliate link's sub_id so a future commission can be attributed to this channel in the Travelpayouts dashboard. Defaults to 'direct'. Sanitized to [a-z0-9-]; capped at 64 chars."New value: +"Acquisition channel tag (e.g. web, mcp, a campaign name) for first-party analytics. Durable booking links retain the validated Travelpayouts marker for commission but do not trust opaque shortlinks solely to carry provider-dashboard sub_id attribution. Defaults to 'direct'; reduced to a bounded registered channel." - changed
Input schema / properties / verify / descriptionPrevious value: -"How hard to cross-check the top result's route, dates, and cabin against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget (set it when you can wait, e.g. an autonomous agent). This does not verify the displayed airline, itinerary, gate, or booking URL; inspect `metadata.route_price_check` separately. Checked-bag searches keep this fare-only route check and verdict null even when verify=true or verify=full; seller-level baggage enrichment still runs. Displayed Travelpayouts fares remain explicitly labeled cached indicators. No-op unless a SerpApi key is configured."New value: +"How hard to cross-check the top result's route, dates, and cabin against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget and widen the request-local seller/date sample from at most three pairs to at most seven (set it when you can wait, e.g. an autonomous agent). The six-hour base and its cache key do not change. This does not verify the displayed airline, itinerary, gate, or booking URL; inspect `metadata.route_price_check` separately. Checked-bag searches keep this fare-only route check and verdict null even when verify=true or verify=full; seller-level baggage enrichment still runs. Displayed Travelpayouts fares remain explicitly labeled cached indicators. No-op unless a SerpApi key is configured."
1 tool update
- Changed
search_flights3 fields changed- changed
Input schema / properties / cabin / descriptionPrevious value: -"Cabin class: economy (default), premium_economy, business, or first. The bookable Travelpayouts calendar currently covers economy only. For a non-economy request, Google Flights may return representative route/date/cabin evidence in metadata.route_price_check, but no ranked fare is shown unless an exact seller booking action is available."New value: +"Cabin class: economy (default), premium_economy, business, or first. The Travelpayouts calendar covers economy; Google Flights may additionally return action-bound seller quotes for the requested cabin. Actionless evidence remains in metadata.route_price_check." - added
Input schema / properties / checked_bagsAdded value: +{ + "default": 0, + "description": "Checked bags requested for the current one-adult, specific-route search contract. Anywhere discovery rejects checked_bags=1. Set to 1 to add a seller's unambiguous first-checked-bag fee to the ranked customer price. Unknown fees remain labeled in results[].price_basis instead of being guessed. Seller enrichment still runs, but the fare-only verdict and route-price check remain null, including when verify=true or verify=full.", + "examples": [ + 0, + 1 + ], + "maximum": 1, + "minimum": 0, + "title": "checked_bags", + "type": "integer" +} - changed
Input schema / properties / verify / descriptionPrevious value: -"How hard to cross-check the top result's route, dates, and cabin against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget (set it when you can wait, e.g. an autonomous agent). This does not verify the displayed airline, itinerary, gate, or booking URL; inspect `metadata.route_price_check` separately. Displayed Travelpayouts fares remain explicitly labeled cached indicators. No-op unless a SerpApi key is configured."New value: +"How hard to cross-check the top result's route, dates, and cabin against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget (set it when you can wait, e.g. an autonomous agent). This does not verify the displayed airline, itinerary, gate, or booking URL; inspect `metadata.route_price_check` separately. Checked-bag searches keep this fare-only route check and verdict null even when verify=true or verify=full; seller-level baggage enrichment still runs. Displayed Travelpayouts fares remain explicitly labeled cached indicators. No-op unless a SerpApi key is configured."
2 tool updates
- Changed
search_flights4 fields changed- changed
Input schema / properties / from / descriptionPrevious value: -"Origin airport, 3-letter IATA code, UPPERCASE. Required for every search, including to=anywhere."New value: +"Origin location. Use a legacy 3-letter code (SHA), an exact airport (airport:SHA), or an all-airports city (city:SHA). Required for every search, including to=anywhere." - changed
Input schema / properties / from / examplesPrevious value: -[ - "SGN", - "HKG", - "BKK" -]New value: +[ + "SGN", + "airport:SHA", + "city:SHA" +] - changed
Input schema / properties / to / descriptionPrevious value: -"Destination airport, 3-letter IATA code, UPPERCASE. Pass `anywhere` (or omit) to get the cheapest destinations from the origin instead of a specific route."New value: +"Destination location: a legacy code, airport:AAA, or city:AAA. Pass `anywhere` (or omit) to get the cheapest destinations from the origin instead of a specific route." - changed
Input schema / properties / to / examplesPrevious value: -[ - "ICN", - "NRT", - "SIN", - "anywhere" -]New value: +[ + "ICN", + "airport:PVG", + "city:BJS", + "anywhere" +]
- Added
search_locations
1 tool update
- Changed
search_flights2 fields changed- changed
Input schema / properties / cabin / descriptionPrevious value: -"Cabin class: economy (default), premium_economy, business, or first. Use cabin=business to find business-class deals — the price verdict then judges the fare against the route's typical BUSINESS prices, and metadata.deal_signal flags a business fare below its own typical band. Non-economy cabins are priced via the live Google Flights source only (the cached calendar source covers economy), so results sample representative dates in the window."New value: +"Cabin class: economy (default), premium_economy, business, or first. The bookable Travelpayouts calendar currently covers economy only. For a non-economy request, Google Flights may return representative route/date/cabin evidence in metadata.route_price_check, but no ranked fare is shown unless an exact seller booking action is available." - changed
Input schema / properties / verify / descriptionPrevious value: -"How hard to live-verify the top result against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget (set it when you can wait, e.g. an autonomous agent). Always inspect `metadata.freshness`: if the live source is unavailable, fails, or reaches its spend cap, the response can still contain explicitly labeled cached indicators. No-op unless a SerpApi key is configured."New value: +"How hard to cross-check the top result's route, dates, and cabin against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget (set it when you can wait, e.g. an autonomous agent). This does not verify the displayed airline, itinerary, gate, or booking URL; inspect `metadata.route_price_check` separately. Displayed Travelpayouts fares remain explicitly labeled cached indicators. No-op unless a SerpApi key is configured."
1 tool update
- Changed
search_flights4 fields changed- changed
Input schema / properties / latest / descriptionPrevious value: -"Latest acceptable return date (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Required for a specific route; ignored in anywhere mode."New value: +"Latest acceptable return date for round-trip, or latest acceptable departure for one-way (ISO YYYY-MM-DD). Window from earliest must be ≤365 days. Required for a specific route; ignored in anywhere mode." - changed
Input schema / properties / max_days / descriptionPrevious value: -"Maximum trip duration in days (return - departure)."New value: +"Maximum round-trip duration in days (return - departure); ignored for one-way and anywhere mode." - changed
Input schema / properties / min_days / descriptionPrevious value: -"Minimum trip duration in days (return - departure)."New value: +"Minimum round-trip duration in days (return - departure); ignored for one-way and anywhere mode." - changed
Input schema / properties / top_n / descriptionPrevious value: -"Maximum number of results to return, sorted cheapest-first."New value: +"Maximum number of results to return, sorted cheapest-first. Specific routes allow up to 50; anywhere mode returns at most 12."
1 tool update
- Changed
search_flights4 fields changed- removed
Input schema / properties / from / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - changed
Input schema / properties / from / descriptionPrevious value: -"Origin airport, 3-letter IATA code, UPPERCASE. Required for a specific route; with to=anywhere it may be omitted to auto-detect from the caller's IP country."New value: +"Origin airport, 3-letter IATA code, UPPERCASE. Required for every search, including to=anywhere." - changed
Input schema / properties / verify / descriptionPrevious value: -"How hard to live-verify the top result against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — wait for complete live verification and return the freshest prices with NO cached_indicators fallback (a longer ~35s budget; set it when you can wait, e.g. an autonomous agent). No-op unless a SerpApi key is configured."New value: +"How hard to live-verify the top result against Google Flights (SerpApi). `false` (default): the check still runs automatically on a fresh search when the top isn't already a live price, within a client-aware time budget. `true`: force the check even on a cache hit. `full`: THOROUGH mode — force the same best-effort check with a longer ~35s budget (set it when you can wait, e.g. an autonomous agent). Always inspect `metadata.freshness`: if the live source is unavailable, fails, or reaches its spend cap, the response can still contain explicitly labeled cached indicators. No-op unless a SerpApi key is configured." - added
Input schema / requiredAdded value: +[ + "from" +]
1 tool update
- First observed
search_flights
Related MCP Connectors
Flight search & booking for AI agents. 400+ airlines, $20-50 cheaper than OTAs.
Flight search, airfare analytics, flexible destinations
Brazil-first flight price search for AI agents: Portuguese place names, BRL, disclosed affiliate
Search and compare flight offers through a cache-aware Streamable HTTP MCP server for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceFlexible multi-leg, multi-airport flight search that finds the cheapest route across an entire itinerary — available as a CLI and as an MCP server for AI agents.Apache 2.0
- AlicenseAqualityDmaintenanceIntegrates Google Flights data into AI workflows for natural language flight searches, price comparisons, flexible date searches, and multi-city itinerary planning with support for various cabin classes and passenger types.95MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to search real-time Google Flights data without an API key, covering flight and multi-city searches, cabin class comparisons, 60-day price calendars, SQLite-backed price tracking, emissions and aircraft details, nearby airport lookup, and layover risk analysis.12213 npmISC

FlightClawofficial
AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search, price-track, and book flights across ~300 airlines, with traveler profiles, preferences, and email fare-drop alerts.74MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.