Google Flights MCP

Eight agent skills that turn real-time Google Flights and Booking.com pricing into travel answers — the cheapest date to fly, where to go, a whole trip budget, a fare watch, a hotel shortlist, a rate-parity audit, and a client-ready write-up.

Start with the hosted server, not the repo.One line and any MCP client can search live flights:

claude mcp add --transport http google-flights https://google-flights-mcp.flightpowers.com/mcp --header "x-rapidapi-key: YOUR_RAPIDAPI_KEY"

That gives your agent the data. The skills below are what make itusethe data well — one call for a whole date range instead of thirty, thelow | typical | highverdict instead of a bare number, and a fresh fetch every time instead of a stale fare.

One hub holds auth, hosts, every endpoint, every response field name, and the billing rules. Seven workflow skills stay thin and delegate to it.

travel-data-api hub — auth, hosts, endpoints, response fields, cost per call |- cheapest-dates WHEN to fly: scan a date range, judge the winner |- destination-compare WHERE to go: price many cities from one origin |- trip-planner flights + hotel totalled into one all-in budget |- fare-watch one pinned route, re-checked over time, book-now-or-wait |- hotel-search find and price places to stay |- rate-parity-monitor same hotel priced as a resident of each country - travel-brief presentation layer — recommendation, table, links

claude plugin marketplace add mtnrabi/travel-agent-skills claude plugin install travel-agent-skills@travel-agent-skills

Restart Claude Code and all eight skills load together — the agent picks the right one from the question, and you can also invoke one directly by name (cheapest-dates,trip-planner,rate-parity-monitor).

git clone https://github.com/mtnrabi/travel-agent-skills.git # personal, every project: cp -r travel-agent-skills/skills/ ~/.claude/skills/ # or scoped to one project: mkdir -p .claude/skills && cp -r travel-agent-skills/skills/ .claude/skills/

Each skill is a self-contained folder with aSKILL.mdand anagents/openai.yamldisplay descriptor, so any runtime that reads a skills directory can load them — copy the whole set, or just the folders you want. Nothing here imports anything; there is no build step and no dependency.

cp .env.example .env # then paste your key into RAPIDAPI_KEY

claude mcp add --transport http google-flights https://google-flights-mcp.flightpowers.com/mcp --header "x-rapidapi-key: YOUR_RAPIDAPI_KEY"

Two tools,search_oneway_flightsandsearch_roundtrip_flights. Both take adate range(departure_date_from/departure_date_to), alistof destinations, and — for round-trip —nights(a number, or a list like[5,6,7]) instead of a fixed return date. One user intent is one tool call, never one call per date. If your client does not do custom headers, the paid server also accepts?rapidapi_key=on the URL or an API-key field where the client offers one.

- price_insights_low/price_insights_high/price_range_in_relation_to_other_periods— Google's own historical price band for that route and period, plus alow | typical | highverdict. That is the difference between "$209" and "$209 is typical for this route — no need to rush". Every flight skill leads with the verdict, not the number.
- proxy_countryon the hotel endpoints routes the request through a residential proxy in that country, so the same hotel and dates can be priced as a user inus,de, orilwould see them. That is what makesrate-parity-monitorpossible.

I'm flexible — cheapest 4 nights in Paris out of Berlin, sometime in the first half of June. Is it actually a good price, or should I wait?

cheapest-datesrecognises the flexible window, issuesonesearch_roundtrip_flightscall withdeparture_date_from: 2026-06-01,departure_date_to: 2026-06-15andnights: 4, sorts the results itself, then answers in this shape:

Low for this route. $119 round-trip sits under Google's historical band of $135–$205 for BER–CDG in this period — this is a book-it price, not a wait-it-out price. Best: depart Mon Jun 1, return Fri Jun 5 (4 nights) Out easyJet · non-stop · 1 hr 50 min · 7:00 AM → 8:50 AM Back easyJet · non-stop · 1 hr 45 min · 8:20 PM → 10:05 PM Total $119 · https://www.google.com/travel/flights?tfs=... Runner-up dates, cheapest per departure day: Jun 2 $131 Jun 8 $146 Jun 11 $158 Jun 4 $172 Prices checked at 2026-06-01 09:14 UTC — fares go stale in minutes.

Three things in that answer are the whole point of the skills:
- One call, not fifteen.A fifteen-day window over REST is fifteen billed requests; over MCP with a range it is one. The skill says the request count out loudbeforeit spends your money.
- The verdict leads.A scan always produces a minimum — a minimum is not a deal. If the cheapest date found comes backtypicalorhigh, the skill says so.
- Nothing is reused.Ask again an hour later and it re-fetches and re-stamps. No skill in this repo caches a fare, and every answer carries the time it was fetched.

Where can I go from JFK for under $400 in late October? Somewhere warm. Watch BER→LHR for the 14th and ping me if it drops below $90. Plan a week in Rome in May for two, £1800 all in, hotel needs free cancellation. Is the Hilton Paris Opera cheaper booked from Germany than from the US, same dates? Write up the Lisbon options for my client with a table and booking links.

- Prefer the MCP tools when a client has them; fall back to REST curl otherwise. Hotels are always REST.
- Say what a call costsbeforemaking it. Every billed request is the user's money.
- An empty result is[]with HTTP 200 — that means "no flights on this route and date", not an error. Report it and move on; do not retry in a loop.
- Never cache or reuse a fare from earlier in the conversation. Always stamp the answer with when the data was fetched.
- Lead with the answer, then the evidence. Never present abuy_link`as a held, locked, or guaranteed fare.
- Never print, log, or commit an API key.

These are independent APIs that return publicly available flight and hotel pricing. They are not affiliated with, endorsed by, or sponsored by Google or Booking.com.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Fetch, convert, and search AWS documentation pages, with recommendations for related content.

Search campgrounds around the world on campertunity, check availability, and provide booking links.

The Ferryhopper MCP Server exposes ferry routes, schedules and booking redirects so an AI assistant can discover connections across Europe and the Mediterranean and send users to Ferryhopper to complete bookings.

All-in-One SEO & Web Intelligence Toolkit API from FetchSERP.

MCP server that provides read-only access to HyperKitty, the web-based email archive component of Mailman 3.

At Sunrise Apps, we believe AI agents should be limitless, especially when it comes to visual data. We created ImageSorcery to bridge the critical gap in AI's ability to interact with and manipulate images directly, all while upholding the highest standards of privacy and security.

Just Domain is the domain registrar for businesses built with AI. Its remote MCP server checks availability and returns first-year and renewal pricing, plus a link to register on justdomain.ai, with DNS and WHOIS privacy in the same place. No account, no API key, read only. Endpoint: https://mcp.justdomain.ai/

Search the web using Kagi's search API

Research tools, including a Sqlite-backed document stash