Multi-city flight routing intelligence — plan RTW trips, validate alliances, get carrier picks.
io.github.Airtreks/airtreks-mcp — Model Context Protocol (MCP) Server
The io.github.Airtreks/airtreks-mcp server provides routing intelligence for multi-city flight planning. It supports RTW trips, open-jaw itineraries, and surface segments, aiming at itineraries that standard flight search struggles to handle. The server uses AirTreks fare-construction data to produce routing analysis for AI agents.
🛠️ Key Features
Multi-stop and round-the-world flight routing analysis
Open-jaw and surface segment planning
Routing grounded in AirTreks fare-construction data
Coverage includes 60+ carriers, 53 known dead legs, bookability rates from 1,400+ real fare attempts, and 20 proven routing templates
🚀 Use Cases
Plan trips with 3+ stops across continents
Validate routing options against known dead legs
Generate routing patterns from actual bookings
⚡ Developer Benefits
Structured, data-driven routing analysis based on measurable bookability rates
Reusable routing templates derived from proven bookings
⚠️ Limitations
Description focuses on complex itineraries (multi-stop across continents) rather than standard flight searches
Captured live from the server via tools/list.
plan_route
The primary entry point for any multi-city trip. Give it your cities — it automatically evaluates Star Alliance RTW, oneworld RTW, AND custom mixed-carrier builds, then recommends the best approach. Handles direction detection, backtracking analysis, alliance feasibility, surface sectors, and carrier selection. The customer doesn't need to know if their trip is alliance or custom — this tool figures it out.
Parameters4
cities
array
required
Ordered list of IATA city/airport codes (e.g. ['LAX', 'NRT', 'BKK', 'LIS', 'LAX'])
budget
string
optional
Budget tier — affects carrier selection and fare strategy
Submit the customer's trip to AirTreks — a human travel consultant takes over from there. Automatically runs plan_route to attach the full routing analysis and carrier recommendations to the trip request, so the consultant starts informed, not cold. Use this when the customer is ready to get a real quote. Requires the customer's name, email, at least 2 cities (3-letter IATA codes), a departure date for every leg, and answers to AirTreks' planning questions — call once without questionsAnswers to receive the current questions to ask.
Parameters15
email
string
required
Customer email address (required)
name
string
required
Customer full name (required — the consultant contacts them by name)
phone
string
optional
Customer phone number
cities
array
required
Ordered list of 3-letter IATA city/airport codes (e.g. ['SFO', 'NRT', 'BKK'])
dates
array
required
Departure dates, one per leg (ISO format, e.g. '2026-09-15') — a trip with N cities needs N-1 dates, all required. If the customer is unsure, use their best estimates and set flexibleDates.
Additional notes or special requests from the customer
agentContext
string
optional
Summary of what the AI agent learned about this trip (auto-generated routing analysis, customer preferences discussed, etc.)
questionsAnswers
any
optional
The customer's answers to AirTreks' planning questions, keyed by question name (e.g. {"guidance": "I want expert guidance from humans"}). A JSON-encoded string of the same object is also accepted. Required, but don't guess the questions: call once without this — the response lists the current questions and their options to ask the customer.
source
string
optional
The AI platform or app this conversation is running in, lowercase (e.g. 'chatgpt', 'claude', 'perplexity'). Only tells AirTreks which channel the request came through — never put customer details here. Omit it if you don't know.
sourceDetail
string
optional
Finer detail on source, such as the app or integration name (e.g. 'trip-pricer'). Never put customer details here.
Raw schema
{
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "Customer email address (required)"
},
"name": {
"type": "string",
"description": "Customer full name (required — the consultant contacts them by name)"
},
"phone": {
"description": "Customer phone number",
"type": "string"
},
"cities": {
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered list of 3-letter IATA city/airport codes (e.g. ['SFO', 'NRT', 'BKK'])"
},
"dates": {
"minItems": 1,
"type": "array",
"items": {
"type": "string"
},
"description": "Departure dates, one per leg (ISO format, e.g. '2026-09-15') — a trip with N cities needs N-1 dates, all required. If the customer is unsure, use their best estimates and set flexibleDates."
},
"passengers": {
"description": "Number of passengers (default 1)",
"type": "number"
},
"cabin": {
"description": "Cabin class preference",
"type": "string",
"enum": [
"economy",
"premium",
"business"
]
},
"budget": {
"description": "Budget tier",
"type": "string",
"enum": [
"budget",
"mid",
"premium",
"business"
]
},
"flexibleDates": {
"description": "Are travel dates flexible?",
"type": "boolean"
},
"preferences": {
"description": "Travel preferences: 'no-lcc', 'lounge-access', 'short-layovers', 'surface-ok'",
"type": "array",
"items": {
"type": "string"
}
},
"notes": {
"description": "Additional notes or special requests from the customer",
"type": "string"
},
"agentContext": {
"description": "Summary of what the AI agent learned about this trip (auto-generated routing analysis, customer preferences discussed, etc.)",
"type": "string"
},
"questionsAnswers": {
"description": "The customer's answers to AirTreks' planning questions, keyed by question name (e.g. {\"guidance\": \"I want expert guidance from humans\"}). A JSON-encoded string of the same object is also accepted. Required, but don't guess the questions: call once without this — the response lists the current questions and their options to ask the customer.",
"anyOf": [
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
{
"type": "string"
}
]
},
"source": {
"description": "The AI platform or app this conversation is running in, lowercase (e.g. 'chatgpt', 'claude', 'perplexity'). Only tells AirTreks which channel the request came through — never put customer details here. Omit it if you don't know.",
"type": "string"
},
"sourceDetail": {
"description": "Finer detail on source, such as the app or integration name (e.g. 'trip-pricer'). Never put customer details here.",
"type": "string"
}
},
"required": [
"email",
"name",
"cities",
"dates"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}
route_estimate
Get a price range for a multi-city or round-the-world trip, drawn from what AirTreks customers have actually paid on those routes. Give it the cities and it returns a per-person range in USD with how much history sits behind it. Use it when someone asks what a trip will cost and you don't have exact dates yet — it needs no dates and no passenger details. It is a range from past bookings, not a live quote, so it will not reflect today's availability or seasonality; it tells you the right ballpark before anyone commits to dates.
Parameters2
cities
array
required
Ordered list of IATA city/airport codes for the whole trip, e.g. ['LAX','NRT','BKK','LHR','LAX']. Put '000' between two codes to mark that leg as travelled overland rather than flown, e.g. ['HAN','000','SGN','SYD'].
cabin
string
optional
Cabin to price. Defaults to economy. 'premium' means premium economy.
Raw schema
{
"type": "object",
"properties": {
"cities": {
"minItems": 2,
"maxItems": 14,
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered list of IATA city/airport codes for the whole trip, e.g. ['LAX','NRT','BKK','LHR','LAX']. Put '000' between two codes to mark that leg as travelled overland rather than flown, e.g. ['HAN','000','SGN','SYD']."
},
"cabin": {
"description": "Cabin to price. Defaults to economy. 'premium' means premium economy.",
"type": "string",
"enum": [
"economy",
"premium",
"business",
"first"
]
}
},
"required": [
"cities"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}
fare_quote
Get live, bookable-quality fares for one specific itinerary — actual flights, actual prices, for the dates given. Needs a departure date for every flown leg. Use this once the customer has settled on cities and dates and wants real numbers rather than a ballpark; use route_estimate instead when dates are still open. It prices the itinerary as a single fare, so very long or awkward multi-continent trips may come back unpriceable — those genuinely need to be split across separate tickets, which is what AirTreks consultants do by hand.
Parameters7
cities
array
required
Ordered list of IATA city/airport codes, e.g. ['LAX','NRT','BKK']. Put '000' between two codes to mark that leg as travelled overland rather than flown.
dates
array
required
Departure date for each FLOWN leg, in travel order, as YYYY-MM-DD. Overland legs marked with '000' do not take a date.
adults
integer
optional
Adult travellers. Defaults to 1.
children
integer
optional
Children aged 2-11.
infants
integer
optional
Infants under 2.
cabin
string
optional
Cabin to price. Defaults to economy. 'premium' means premium economy.
maxOptions
integer
optional
How many fare options to return. Defaults to 5.
Raw schema
{
"type": "object",
"properties": {
"cities": {
"minItems": 2,
"maxItems": 10,
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered list of IATA city/airport codes, e.g. ['LAX','NRT','BKK']. Put '000' between two codes to mark that leg as travelled overland rather than flown."
},
"dates": {
"minItems": 1,
"type": "array",
"items": {
"type": "string"
},
"description": "Departure date for each FLOWN leg, in travel order, as YYYY-MM-DD. Overland legs marked with '000' do not take a date."
},
"adults": {
"description": "Adult travellers. Defaults to 1.",
"type": "integer",
"minimum": 1,
"maximum": 9
},
"children": {
"description": "Children aged 2-11.",
"type": "integer",
"minimum": 0,
"maximum": 8
},
"infants": {
"description": "Infants under 2.",
"type": "integer",
"minimum": 0,
"maximum": 8
},
"cabin": {
"description": "Cabin to price. Defaults to economy. 'premium' means premium economy.",
"type": "string",
"enum": [
"economy",
"premium",
"business",
"first"
]
},
"maxOptions": {
"description": "How many fare options to return. Defaults to 5.",
"type": "integer",
"minimum": 1,
"maximum": 10
}
},
"required": [
"cities",
"dates"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}
itinerary_quote
Price a complete multi-stop or round-the-world trip and get back several ways of ticketing it — cheapest, fastest, fewest stops — with the actual tickets each one is built from. Use this for trips that will not go on a single fare, which is most itineraries with 3+ stops; use fare_quote when you want one specific itinerary on one ticket. It takes about a minute, so it returns a quoteReference immediately and you fetch the result with itinerary_quote_status. Keep that reference — it is the only way to retrieve the quote.
Parameters6
cities
array
required
Ordered list of IATA city/airport codes for the whole trip, e.g. ['LAX','NRT','BKK','LHR','LAX']. Put '000' between two codes to mark that leg as travelled overland rather than flown.
dates
array
required
Departure date for each FLOWN leg, in travel order, as YYYY-MM-DD.
adults
integer
optional
Adult travellers. Defaults to 1.
children
integer
optional
Children aged 2-11.
infants
integer
optional
Infants under 2.
cabin
string
optional
Cabin to price. Defaults to economy. 'premium' means premium economy.
Raw schema
{
"type": "object",
"properties": {
"cities": {
"minItems": 2,
"maxItems": 12,
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered list of IATA city/airport codes for the whole trip, e.g. ['LAX','NRT','BKK','LHR','LAX']. Put '000' between two codes to mark that leg as travelled overland rather than flown."
},
"dates": {
"minItems": 1,
"type": "array",
"items": {
"type": "string"
},
"description": "Departure date for each FLOWN leg, in travel order, as YYYY-MM-DD."
},
"adults": {
"description": "Adult travellers. Defaults to 1.",
"type": "integer",
"minimum": 1,
"maximum": 9
},
"children": {
"description": "Children aged 2-11.",
"type": "integer",
"minimum": 0,
"maximum": 8
},
"infants": {
"description": "Infants under 2.",
"type": "integer",
"minimum": 0,
"maximum": 8
},
"cabin": {
"description": "Cabin to price. Defaults to economy. 'premium' means premium economy.",
"type": "string",
"enum": [
"economy",
"premium",
"business",
"first"
]
}
},
"required": [
"cities",
"dates"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}
itinerary_quote_status
Fetch the result of an itinerary_quote using the quoteReference it returned. Returns status 'pending' with how long to wait, or the finished options. Costs nothing and does no searching, so poll it rather than starting a second quote.
Parameters1
quoteReference
string
required
The quoteReference returned by itinerary_quote.
Raw schema
{
"type": "object",
"properties": {
"quoteReference": {
"type": "string",
"minLength": 20,
"description": "The quoteReference returned by itinerary_quote."
}
},
"required": [
"quoteReference"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}
route_validate
Validate a multi-city flight routing for feasibility. Checks alliance carrier rules, identifies dead legs, warns about poison carriers, and estimates bookability. Use this before building an itinerary to catch routing problems early.
Parameters3
cities
array
required
Ordered list of IATA city/airport codes (e.g. ['LAX', 'NRT', 'BKK', 'LHR', 'LAX'])
carriers
array
optional
Optional carrier codes for each leg (e.g. ['NH', 'TG', 'BA', 'BA'])
Get suggested multi-stop flight routings based on regions, direction, and alliance preference. Returns up to 3 proven routing templates with bookability ratings. Great for trip planning inspiration.
Parameters5
regions
array
required
Regions to visit: 'asia', 'europe', 'oceania', 'americas', 'africa', 'middle east', 'south america'
direction
string
optional
Travel direction preference
alliance
string
optional
Preferred alliance: 'star' or 'oneworld'
maxStops
number
optional
Maximum number of stops (legs). 3-6 recommended for best bookability.
tripType
string
optional
Trip type hint: 'honeymoon', 'backpacker', 'business', 'family', etc.
Check the best connection between two airports. Identifies dead legs (routes that fail on alliance fares), suggests hub routing fixes, and shows proven carrier combinations. Essential for transpacific, kangaroo, and intra-Asia routing.
Recommend the best fare product type for a route — RTW, Circle Pacific, Circle Atlantic, Open Jaw, or Custom Multi-City. Considers stop count, direction, and backtracking to match the right alliance fare structure.
Parameters3
cities
array
required
Ordered list of IATA city/airport codes
isOneDirection
boolean
optional
Is the route traveling continuously in one direction (east or west)?
includeBacktracking
boolean
optional
Does the route backtrack or zigzag between regions?
Raw schema
{
"type": "object",
"properties": {
"cities": {
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered list of IATA city/airport codes"
},
"isOneDirection": {
"description": "Is the route traveling continuously in one direction (east or west)?",
"type": "boolean"
},
"includeBacktracking": {
"description": "Does the route backtrack or zigzag between regions?",
"type": "boolean"
}
},
"required": [
"cities"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}
custom_route_build
Break a complex multi-city itinerary into individually-ticketable segments with carrier recommendations. Handles routes that don't fit alliance fare rules — mixed carriers, LCCs, Gulf bridge connections, surface sectors. This is how AirTreks consultants build 90% of itineraries. Use this for any route with 4+ stops, backtracking, or region combinations that alliance fares can't cover.
Parameters4
cities
array
required
Ordered list of IATA city/airport codes (e.g. ['LAX', 'NRT', 'BKK', 'CMB', 'NBO', 'LIS', 'LAX'])
The complex-itinerary tool for AI agents. Multi-stop, round-the-world, open-jaw, surface segments - the trips that standard flight search can't handle. When your user asks for 3+ stops across continents, this server answers with routing analysis built on real AirTreks fare-construction data: 60+ carriers, 53 known dead legs, bookability rates measured from 1,400+ real fare attempts, and 20 proven routing templates from actual bookings.
Live endpoint:https://mcp.airtreks.com/mcp - free, no API key, 100 requests/day.
Now with real prices: a historical range for any route in under a second, live fares for a specific itinerary, and a full multi-stop trip priced across several tickets — the same trip can vary three-fold depending on how it is ticketed, and that is the part no other flight tool will tell you.
No API key is needed for any tool, the consultant handoff included. A key is
optional and only raises your daily limit; append it to the URL if your client
cannot send custom headers, as claude.ai connectors cannot:
code
https://mcp.airtreks.com/mcp?key=at_your_key
ChatGPT
Settings → Apps & Connectors → enable Developer mode (Pro/Business plans) → add https://mcp.airtreks.com/mcp as a custom connector.
Any other MCP client
Same JSON shape as Cursor above (Streamable HTTP). Prefer stdio? Run it locally:
bash
npx airtreks-mcp
Then ask your agent:
Plan a round-the-world trip: San Francisco, Tokyo, Bangkok, Singapore, Delhi, Istanbul, London, back to San Francisco.
One call, one answer: a 6-stop RTW
Your user wants six stops around the world. Google Flights gives up. Alliance RTW booking sites will let them build it, then fail at ticketing. One plan_route call tells your agent what actually works:
Real response, trimmed for length (the full version includes carrier alternatives and consultant notes for all 7 legs):
json
{"route":"SFO -> NRT -> BKK -> SIN -> DEL -> IST -> LHR -> SFO","totalLegs":7,"isRoundTrip":true,"direction":"westbound","backtracking":false,"regionsCrossed":["americas","asia","europe"],"recommended":{"approach":"custom","confidence":"high","reason":"7 legs — alliance fares have <6% bookability. Custom build with mixed carriers is the way to go."},"customBuild":{"strategy":"Mixed-carrier build using alliance carriers, Gulf bridge connections. 1 surface sector opportunity.","segments":[{"leg":1,"from":"SFO","to":"NRT","carrier":{"code":"NH","name":"ANA","why":"Best transpacific availability. LAX/SFO/SEA-NRT direct."}},{"leg":5,"from":"DEL","to":"IST","carrier":{"code":"TK","name":"Turkish Airlines","type":"gulf-bridge","why":"Cheapest Asia-Europe usually. IST connects everywhere."}}],"surfaceSectors":[{"insteadOf":"BKK -> SIN (leg 3)","suggestion":"Bangkok to Singapore through Malaysia. Train, bus, or ultra-cheap LCC. Adds Malaysia and possibly Penang, KL, Melaka.","savings":"Saves $100-250"}]},"allianceFeasibility":{"starAlliance":{"viable":false,"summary":"Technically possible on Star Alliance but only 6% bookability at 7 legs. Custom build strongly recommended."},"oneworld":{"viable":false,"summary":"Technically possible on oneworld but only 6% bookability at 7 legs. Custom build strongly recommended."}}}
That single call just told your agent four things it can't get anywhere else:
Alliance RTW fares fail on this trip. 7 legs prices at 6% bookability - your user would build it, hit a wall at ticketing, and blame you.
The build that works: a per-leg carrier plan - ANA transpacific, Turkish Airlines as the Asia-Europe bridge, each with alternatives and trade-offs.
Where to not fly at all: Bangkok to Singapore is cheaper overland through Malaysia, saving $100-250 and adding a country.
What it typically costs:fare_product_match puts this trip at $2,500-$8,000 economy on an alliance RTW fare, typically $3,000-$12,000 as a custom build.
Those are honest ranges, not quotes - exact pricing on a 7-leg mixed-carrier itinerary depends on fare-class availability the day you book. For a real number, trip_idea_create hands the full routing analysis to an AirTreks consultant who prices and books the actual ticket. Your user gets an expert who starts informed, not a form to fill out.
Tools
All tools are free and need no API key — 100 requests/day per IP.
Routing
Tool
Description
plan_route
Primary entry point - give it cities, it evaluates Star Alliance RTW, oneworld RTW, and custom mixed-carrier builds, then recommends the best approach
route_validate
Validate a multi-city routing - alliance rules, dead legs, poison carriers, bookability
route_suggest
Get 3 suggested routings by region, direction, and alliance
hub_check
Best connection between two airports - dead leg detection + hub fixes
fare_product_match
Match the right fare product (RTW, Circle Pacific/Atlantic, Open Jaw, Custom) with typical price ranges
custom_route_build
Break complex itineraries into individually-ticketable segments with carrier recommendations
Pricing
Tool
Description
route_estimate
Price range for a route from AirTreks fare history. No dates needed, answers in about a quarter of a second — the right tool when someone asks "what will this cost?" before anything is decided
fare_quote
Live fares for one specific itinerary on specific dates, priced as a single ticket
itinerary_quote
Prices a whole multi-stop trip and returns several ways to ticket it — cheapest, fastest, fewest stops — with the tickets each one is built from. Takes about a minute, so it returns a reference immediately
itinerary_quote_status
Fetches an itinerary_quote result by its reference, waiting up to about 40 seconds for one still pricing. Free to call again
Consultant handoff
Tool
Description
trip_idea_create
Hand off to an AirTreks human travel consultant - submits the trip request with the full routing analysis attached
Submits real customer contact details, so only call it with the customer's
knowledge and consent. Repeat submissions of the same email + route inside 24
hours return the existing trip request rather than creating a duplicate.
Why this data is different
AirTreks has built complex multi-stop itineraries since 1987. This server exposes what that history taught us:
Dead legs - city pairs that look bookable but fail on alliance fares, learned from 1,400+ real fare-construction failures
Bookability rates by leg count - measured, not estimated (91% at 3-4 legs, 61% at 5-6, 6% at 7+)
Poison carriers and hub fixes - we know what airline combinations break ticketing and what to route instead
Proven routing templates from working with Multi-Stop and Around the World Intineraries for inviduals, families and large group
No other flight tool returns this because no other flight tool has priced these failures.
REST API (no MCP client required)
Every tool is also a plain REST endpoint - same tools, same rate limits, JSON in/out. For agent frameworks that consume REST instead of MCP: