letsfg
mcpsmitheryAgent-native flight search. 102 airline connectors fire in parallel — Ryanair, EasyJet, Wizz Air, Southwest, AirAsia, Qantas, and 96 more — plus enterprise GDS/NDC providers (Amadeus, Duffel, Sabre, Travelport) through the LetsFG backend. One tool call scans the entire world for flights, including airlines your agent didn't know existed. Your agent doesn't need to build a flight integration. It doesn't need to scrape. Just add this MCP server and it can search and book flights in seconds. ### Why? Flight websites inflate prices with demand tracking, cookie-based pricing, and surge markup. The same flight is often **$20–$50 cheaper** through LetsFG — raw airline price, zero markup. ### How it works `search_flights` fires all relevant connectors in parallel on your machine + queries enterprise GDS sources in the cloud. Results come back merged, deduplicated, sorted by price. ~5 seconds for a full global search. ### Tools | Tool | What it does | Cost | |------|-------------|------| | `search_flights` | Search 400+ airlines | Free | | `search_hotels` | Search hotels worldwide | Free | | `resolve_location` | City/airport → IATA code | Free | | `get_agent_profile` | Your usage & profile | Free | | `unlock_flight_offer` | Confirm live price, reserve 30 min | Free | | `setup_payment` | Attach Stripe payment | Free | | `book_flight` | Book with real PNR + e-ticket | Ticket price only | **Search is free forever. Booking charges the raw airline ticket price via Stripe — we add zero margin.** `LETSFG_API_KEY` is optional. Without it, the server runs all 102 local connectors. With it, you also get 400+ airlines via enterprise GDS/NDC sources. ### Pricing - **Personal use** — completely free. Search, unlock, book. No limits. - **Commercial use** — 1% fee (min $1 USD) per booking, collected via Stripe Connect. Search and unlock are still free. - **First 1,000 GitHub stars** — star the repo and link your GitHub username to get free unlimited access (personal & commercial). No trial, no catch. ### Links - **GitHub:** [github.com/LetsFG/LetsFG](https://github.com/LetsFG/LetsFG) — full docs, 102 connector source code, architecture guide, agent integration tutorials - **API Docs:** [api.letsfg.co/docs](https://api.letsfg.co/docs) - **PyPI:** [pypi.org/project/letsfg](https://pypi.org/project/letsfg/) - **npm:** [npmjs.com/package/letsfg-mcp](https://www.npmjs.com/package/letsfg-mcp)
By Smithery | 13 findings | Scanned 4/19/2026 | tooltrust-scanner/v0.3.8
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (13)
search_flights:tool declares network permission
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
setup_payment:input parameter "token" appears to accept a secret or credential
Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
get_agent_profile:tool declares fs permission
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
search_flightssetup_paymentFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
setup_payment:tool declares http permission
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
search_flightsresolve_locationunlock_flight_offerbook_flightsetup_paymentget_agent_profilesystem_infoFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y letsfg"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)