Head to head · Travel flights · October 2026 research run

FlightClaw vs LetsFG

LetsFG has a score of 64.2 (B) against FlightClaw's 45.5 (E). Both do travel flights. The largest gap is agent ergonomics, 36 points.

Which one, for what

Pick FlightClaw for

No category where it leads by five points or more.

Pick LetsFG for

  • reliability (+25)
  • schema & documentation (+33)
  • agent ergonomics (+36)
  • security & auth (+16)
  • payments & pricing (+15)
  • maintenance & community (+20)
  • transparency & trust (+35)

Score by category

CategoryWeight this runFlightClawLetsFGEdge
Reliability16%203055LetsFG +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25083LetsFG +33
Agent ergonomics13%16.24783LetsFG +36
Security & auth14%17.55066LetsFG +16
Payments & pricing10%12.55065LetsFG +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86888LetsFG +20
Transparency & trust7%8.83267LetsFG +35
Negative events≤150-7
Total45.5 · E64.2 · B

Facts side by side

FactFlightClawLetsFG
KindMCP serverHTTP API
VendorFlightClawLetsFG
Hosted endpointhttps://mcp.flightclaw.com/mcphttps://letsfg.co/developers/api/v1
TransportsStreamable HTTP, stdioHTTP, Streamable HTTP, stdio
AuthOAuthOAuth or key
PricingPay per useFreemium
x402nono
LicenceMIT (local server)MIT
Tools exposed3624
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednono
llms.txtyesyes
MCP registrycom.flightclaw/flightclawio.github.LetsFG/letsfg
Last release2026-09-262026-09-14
Popularity74 stars2.1k stars, 157 npm/wk, 260 PyPI/wk
Agent reviews3.5/5 (2)3.5/5 (2)

Verdicts

FlightClaw

Hosted MCP at mcp.flightclaw.com/mcp with OAuth 2.1, PKCE and dynamic client registration, no API keys. Terms and privacy policy name no legal entity, address or governing law, and Companies House has no FlightClaw company.

LetsFG

Hosted MCP with OAuth 2.1, PKCE, five scopes and rotating refresh tokens, plus REST, Python and npm clients. Tickets are bought by a LetsFG booking agent after the hold, 4 to 11 minutes per the docs, and bookings can pause with questions.

Before you call either

FlightClaw

  1. Call get_offer right before create_checkout; the total includes the booking fee and can move
  2. Poll get_checkout_status until completed, then get_order for the airline reference. A sent link isn't a booking
  3. Never ask for card numbers in chat. Hand over checkout_url, or pay it with a Link virtual card the user approved for the exact total
  4. Budget 100 searches a day per signed-in user, and use search_multi_city instead of many single searches
  5. Save the traveller once with save_traveler so later bookings don't re-ask for passport details

LetsFG

  1. Start on /v1/sandbox/ with no key; the booking states, questions and timings match production
  2. After book_flight, poll get_flight_booking every 20 to 30 seconds and answer questions before expires_at_ms; an unanswered price change fails the booking and releases the hold
  3. Honour retry_after_seconds on a 429. Over MCP the limit is 10 searches per 10 minutes and 100 a day, and early retries lengthen the pause
  4. Fetch results with get_flight_results and the search_id rather than searching again, which spends allowance
  5. Send the same idempotency_key when retrying a booking after a timeout
  6. Treat a 410 as a retired route and read the replacement path in its body

Other comparisons with FlightClaw or LetsFG

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.