Google Hotels Scraper for AI Agents: Live Room Rates via MCP

Photo by Colin Watts on Unsplash

Every LLM can recommend a hotel. None of them know what tonight’s room actually costs. The Google Hotels Scraper on Apify closes that gap: one search returns structured JSON for any destination and date range, with nightly and total prices, guest ratings, star classes, amenities, property details, images, and vacation rentals alongside hotels.

I built it so my agents could quote real rates instead of vibes, and so revenue managers could rate-shop competitors without a Bloomberg-priced tool. Here is what it returns, how to wire it into Claude over MCP, and the examples you can run in one click.

What the Google Hotels Scraper returns

Query any destination the way you would type it into Google (“hotels in Paris”, “Bali resorts”) with check-in and check-out dates and guest counts. Every property row carries the name, nightly and total price, guest rating and review count, star class, amenities, location data, images, and a property token for follow-up lookups.

Filters cover price range, star ratings, amenities, and vacation rentals. Localization covers country (gl), language (hl), and currency (ISO 4217), so “Tokyo hotels priced in yen” is one parameter away. Pricing is pay per event: a search page costs pennies, and you only pay for what you run.

The MCP setup (this is the whole point)

Add one URL to your MCP client config and the scraper becomes a tool your agent can call mid-conversation:

https://mcp.apify.com/?actors=johnvc/google-hotels-search-scraper

Ask “Find me a 4-star in Lisbon under $180 a night for the first weekend of October” and Claude or Cursor comes back with real properties and real prices it can rank and compare, not a paragraph of plausible names.

Who this is for

Hotel revenue managers rate-shopping their comp set. Travel-app builders who need live price data without a sales call. OTA analysts tracking market rates around big events. And AI builders who want their travel agents to quote actual numbers instead of 2023 training data.

Three ready-to-run examples

The Actor ships with three example tasks. Each one is a pre-filled run you can open and start with a single click.

How do I rate-shop competitor hotels?

The competitor rate-shopping task pulls your comp set’s current prices for the dates you care about. Point it at your market, set the dates, and you get a table of who is charging what tonight. Revenue managers pay serious money for this exact report.

How do I search Google Hotels from Claude via MCP?

The Claude via MCP task is the fastest way to see the agent workflow end to end: it shows the exact config and a sample conversation where Claude searches hotels, filters by rating, and quotes prices inline.

How do I track Las Vegas hotel prices for CES week?

The CES week price-tracking task watches Las Vegas rates around the biggest hotel-price spike of the year. Swap in any city and any event; the pattern works for conferences, concerts, and playoff weekends.

Photo by Mohammad Rahmani on Unsplash

Call it from Python

If you want the data in a pipeline instead of a chat, the Apify client is four lines:

from apify_client import ApifyClient
client = ApifyClient("YOUR_API_TOKEN")
run = client.actor("johnvc/google-hotels-search-scraper").call(run_input={"q": "hotels in Lisbon", "check_in_date": "2026-10-02", "check_out_date": "2026-10-04", "adults": 2, "currency": "USD", "stars": "4,5"})
hotels = list(client.dataset(run.default_dataset_id).iterate_items())

FAQ about scraping Google Hotels

Is this Google Hotels scraper an official API?

No. Google offers no public hotels API. This scraper reads the public results page and returns it as structured JSON. Coverage matches what Google Hotels shows for your query, dates, and locale.

Can my AI agent use this Google Hotels scraper over MCP?

Yes. Add it as an MCP tool with the config URL above and Claude, Cursor, or any MCP client can quote live rates mid-conversation. That is the setup I use daily.

Should I build my own Google Hotels scraper?

You can, but date handling, currency localization, vacation-rental toggles, and pagination are constant maintenance. Paying pennies per event beats spending engineering weekends keeping a parser alive.

Can I schedule this Google Hotels scraper to run automatically?

Yes. A nightly rate-shop against your comp set is a two-minute setup in the Apify Console: open the Actor, create a task with your market and dates, and attach a daily schedule. The run history becomes your price-tracking dataset.

If your travel agent quotes prices from 2023 training data, give it tonight’s rates instead. Try the Google Hotels Scraper on a free account and start with the MCP example task.