Travel Hacking Toolkit – Points search and trip planning with AI
Encodes travel hacking math into MCP servers for 25+ mileage programs.
AI-powered travel hacking and search with cash, points, miles, and award flights. Drop-in skills and MCP servers for Claude, Codex, and OpenCode.
MCP servers search award flights and compare cash prices across 25+ mileage programs.
Travel hackers and points/miles enthusiasts who use AI coding assistants
Seats.aero · AwardWallet · Google Flights
This toolkit teaches Claude Code and OpenCode how to do it. 7 skills (markdown files with API docs and curl examples) and 6 MCP servers (real-time tools the AI calls directly).
It searches award flights across 25+ mileage programs (Seats.aero), compares cash prices (Google Flights, Skiplagged, Kiwi.com, Duffel), pulls your loyalty balances (AwardWallet), searches hotels (Trivago, LiteAPI, Airbnb, Booking.com), finds ferry routes across 33 countries, and looks up weird hidden gems near your destination (Atlas Obscura).
Reference data is included: transfer partner ratios for Chase UR, Amex MR, Bilt, Capital One, and Citi TY. Point valuations sourced from TPG, Upgraded Points, OMAAT, and View From The Wing. Alliance membership, sweet spot redemptions, booking windows, hotel chain brand lookups.
5 of the 6 MCP servers need zero API keys. Clone, run setup.sh, start searching.
Skills are, as usual, plain markdown. They work in OpenCode and Claude Code automatically (I added a tiny setup script), and they'll work in anything else that supports skills.
PRs welcome! Help me expand the toolkit! :)
Encodes travel hacking math into MCP servers for 25+ mileage programs.
Another AI travel planner competing with Google Travel and Wanderlog.
First MCP server letting agents book hotels with loyalty points instead of public OTA rates.
Route planner rebuilt in 2 weeks with Deno/Fresh, but Google Maps and Citymapper already own this space.
Clever MCP use case tying to KubeCon's own Agentics Day; hyper-niche and time-limited.
Compiles MCP tools to typed Python to skip model loop, but MCP agents are nascent—adoption depends on platform.