flight-search

Flight Search

Agent-native flight search and booking via the LetsFG cloud engine. Hundreds of airlines, zero markup, $20–50 cheaper than travel websites.

Three-step flow: Search (free) → Unlock (1% of ticket, min $3) → Book (ticket price only)

Why Use This

• Hundreds of airlines — one search covers Europe, Asia, Americas, Middle East, Africa, and Oceania simultaneously
• Zero price bias — no demand inflation, no cookie tracking, no surge pricing. Raw airline prices every time
• Virtual interlining — finds cross-airline connections (e.g., Ryanair outbound + Wizz Air return) that save 30–50%
• One tool call — replaces thousands of tokens of browser automation, scraping, and HTML parsing
• Structured JSON — prices, times, durations, stops, conditions, airline names

Setup

Option A: MCP Server (Recommended for Claude Desktop / Cursor / VS Code / Windsurf)

Remote (no install, always latest):

{
  "mcpServers": {
    "letsfg": {
      "url": "https://letsfg.co/developers/api/mcp",
      "headers": {
        "X-API-Key": "trav_your_api_key"
      }
    }
  }
}

Local (stdio):

{
  "mcpServers": {
    "letsfg": {
      "command": "npx",
      "args": ["-y", "letsfg-mcp"],
      "env": {
        "LETSFG_API_KEY": "trav_your_api_key"
      }
    }
  }
}

Option B: CLI

pip install letsfg
letsfg search LHR BCN 2026-06-15

Option C: Python SDK

from letsfg import LetsFG
bt = LetsFG(api_key="trav_...")
flights = bt.search("LHR", "JFK", "2026-04-15")

Get an API Key (Free)

letsfg register --name my-agent --email agent@example.com

Then attach a payment method (required before unlock):

letsfg setup-payment --token tok_visa

Workflow

1. Resolve Locations First

City names are ambiguous — "London" = LHR, LGW, STN, LCY, LTN. Always resolve first:

letsfg locations "London"
# LON  London (all airports)
# LHR  Heathrow
# LGW  Gatwick

locations = bt.resolve_location("London")
# Use city code "LON" for all airports, or specific airport "LHR"

2. Search (FREE, Unlimited)

flights = bt.search("LON", "BCN", "2026-04-01")
# Round trip:
flights = bt.search("LON", "BCN", "2026-04-01", return_date="2026-04-08")
# Multi-passenger, business class:
flights = bt.search("LHR", "SIN", "2026-06-01", adults=2, children=1, cabin_class="C")

letsfg search LON BCN 2026-04-01 --return 2026-04-08 --sort price --json

Search returns structured offers:

{
  "passenger_ids": ["pas_0"],
  "total_results": 47,
  "offers": [{
    "id": "off_xxx",
    "price": 89.50,
    "currency": "EUR",
    "airlines": ["Ryanair"],
    "route": "STN → BCN",
    "duration_seconds": 7800,
    "stopovers": 0,
    "conditions": {
      "refund_before_departure": "not_allowed",
      "change_before_departure": "allowed_with_fee"
    }
  }]
}

3. Unlock (1% of ticket, min $3)

Confirms live price with airline and reveals the direct booking URL. Locks offer for 30 minutes. Charged to your card (or paid via MPP crypto); free on the prepaid Developer API.

unlocked = bt.unlock(flights.cheapest.id)
print(f"Confirmed: {unlocked.confirmed_price} {unlocked.confirmed_currency}")
print(f"Booking URL: {unlocked.booking_url}")
print(f"Expires: {unlocked.offer_expires_at}")

Note: Confirmed price may differ from search price (airline prices change in real-time). Inform the user if the price changed significantly.

4. Book (Ticket Price Only)

booking = bt.book(
    offer_id=unlocked.offer_id,
    passengers=[{
        "id": flights.passenger_ids[0],
        "given_name": "John",
        "family_name": "Doe",
        "born_on": "1990-01-15",
        "gender": "m",
        "title": "mr",
        "email": "john@example.com"
    }],
    contact_email="john@example.com",
    idempotency_key="unique-booking-key-123"
)
print(f"Booked! PNR: {booking.booking_reference}")

Critical Rules

1. Use REAL passenger details — airlines send e-tickets to the contact email. Names must match passport/ID exactly. Never use placeholder or fake data.
2. Always provide idempotency_key when booking — prevents duplicate reservations if the agent retries on timeout.
3. Resolve locations before searching — "New York" = JFK, LGA, EWR, NYC. Use resolve_location() first.
4. Search is free — search as many routes, dates, and cabin classes as needed.
5. Map passenger IDs — search returns passenger_ids. Each booking passenger must include the correct id.

Best Practices

Search Wide, Unlock Narrow

# Compare multiple dates (all FREE)
dates = ["2026-04-01", "2026-04-02", "2026-04-03"]
best = None
for date in dates:
    result = bt.search("LON", "BCN", date)
    if result.offers and (best is None or result.cheapest.price < best[1].price):
        best = (date, result.cheapest)

# Only unlock the winner
unlocked = bt.unlock(best[1].id)

Filter Before Unlocking

flights = bt.search("LHR", "JFK", "2026-06-01", limit=50)

candidates = [
    o for o in flights.offers
    if o.outbound.stopovers == 0
    and o.outbound.total_duration_seconds < 10 * 3600
]

if candidates:
    best = min(candidates, key=lambda o: o.price)
    unlocked = bt.unlock(best.id)

Finding Connections & Multi-Stop Routes

# Search with stops allowed (default max_stopovers=2)
flights = bt.search("GDN", "BKK", "2026-06-15", max_stopovers=2)

# Filter by connection quality
good_connections = [
    o for o in flights.offers
    if o.outbound.stopovers <= 1
    and o.outbound.total_duration_seconds < 18 * 3600
]

# Virtual interlining finds cross-airline combos automatically
# e.g., Wizz Air GDN→VIE + Thai Airways VIE→BKK

Error Handling

from letsfg import LetsFG, OfferExpiredError, PaymentRequiredError

try:
    unlocked = bt.unlock(offer_id)
except OfferExpiredError:
    # Airline sold the seats — search again
    flights = bt.search(origin, dest, date)
except PaymentRequiredError:
    # No card on file — attach one (or pay via MPP crypto on the 402 challenge)
    print("Attach a card: letsfg setup-payment")

Search Flags

Safety

Reference Files

Load only when needed:

Links

• API Docs: https://letsfg.co/developers/api/docs
• GitHub: https://github.com/LetsFG/LetsFG
• PyPI: https://pypi.org/project/letsfg/
• npm SDK: https://www.npmjs.com/package/letsfg
• npm MCP: https://www.npmjs.com/package/letsfg-mcp