Google Hotels search

Search live Google Hotels stays by location, dates and occupancy, returned in one unified schema alongside every other booking platform. Use when a user wants to find Google Hotels…

stayingapi

@stayingapi

What This Skill Does

Searches live Google Hotels listings by location, dates, and occupancy via the StayingAPI, returning results in a unified schema shared with Airbnb, Booking.com, and Vrbo. Requires a StayingAPI key for authentication.

Replaces manually scraping Google Hotels or building separate integrations for each booking platform by normalizing all results into one consistent data structure.

When to Use It

  • Find Google Hotels properties in a specific city or region for given travel dates
  • Search Google Hotels for accommodations under a budget or with specific filters
  • Compare Google Hotels listings alongside Airbnb, Booking.com, and Vrbo results in one query
  • Discover vacation rentals on Google Hotels for a group with specified adult and child occupancy
  • Search Google Hotels by latitude/longitude coordinates for precise location-based results

Install

$ openclaw skills install @stayingapi/google-hotels-search

Google Hotels search

Search live Google Hotels stays via StayingAPI — one call, the same unified schema you use for Airbnb, Booking.com, Vrbo and Google Hotels.

Setup

If $STAYINGAPI_KEY is not set, read references/auth-setup.md and follow it to get and store the key. A stay_test_ sandbox key works for evaluation at zero cost.

When to use this skill

DO use when the user asks:

  • "Find Google Hotels places in Split, HR for mid-July"
  • "Search Google Hotels for a 2-bed under a budget"

Do NOT use when:

  • A location appears incidentally in conversation
  • The user has one known listing already — use the availability or prices skill

Required headers

Every request needs:

  • Authorization: Bearer $STAYINGAPI_KEY
  • User-Agent: your agent's name (e.g. ClaudeCode/1.0).

Base URL: https://api.stayingapi.com/v1.

Tools

GET /v1/search

Discover properties matching a location, dates, occupancy and filters across one or more platforms. Results from every requested platform are normalized to the same Property shape and merged into a single, cursor-paginated list. This is the breadth / funnel endpoint — and the clearest demonstration of "one schema, every platform".

Key parameters:

  • locationRequired. Place name ("Split, HR") or "lat,lng".
  • checkIn — YYYY-MM-DD; required if checkOut given; not in the past.
  • checkOut — YYYY-MM-DD; required if checkIn given; must be after checkIn.
  • adults — ≥ 1.
  • children — ≥ 0.
  • childAges[] — Length must equal children. Coarsened for Vrbo/Airbnb.
  • platforms[] — Drives fan-out + per-platform billing.

Filter results to Google Hotels by passing platforms=google to the search call.

MCP (no key pasted into the agent)

On an MCP-capable runtime, connect https://mcp.stayingapi.com/mcp (OAuth 2.1 + PKCE) and use: search_stays.

Platform × endpoint support

Not every endpoint supports every platform. Verified:

platformsearchavailabilitypriceprice-comparelistingreviews
airbnbyesyesyesyesyesyes
bookingyesyesyesyesyesyes
vrboyesyesyesyesyesyes
googleyesyesyesyesnono

GET /v1/listing/google/… and GET /v1/reviews?platform=google return 400 platform_not_enabled ("google is not enabled for this endpoint"). Use booking, airbnb or vrbo for listing detail and reviews; use google for search, price and cross-OTA price-compare.

The cross-OTA advantage

StayingAPI is cross-platform: Google Hotels data comes back in the same unified schema as Airbnb, Booking.com and Vrbo, so one integration covers them all. /v1/price-compare resolves a property through the Google Hotels backbone and returns the offers it exposes plus a StayingAPI-computed min and median over those offers, as first-class fields.

Coverage varies by property and by what the backbone returns: some properties come back with several OTA offers, others with a single aggregated-lowest offer (in which case min equals median and offers has one entry, sometimes a direct-supplier rate rather than an OTA). Read offers.length before describing a result as a multi-platform comparison.

Async & partial failures

A live call that has to scrape returns 202 with data.jobId, data.pollUrl and data.estimatedSeconds (the 202 itself charges 0). Poll GET /v1/jobs/{jobId} (free) until data.status is TERMINAL — completed or failed.

  • completed → the payload is at data.result (the same schema the sync call returns; data itself is just {jobId, result, status}). meta carries partial, platformResults[] and warnings[]. A completed job may still return an empty result (data.result: []) — the reason is in meta.warnings[] (e.g. no_results), and empty results charge 0.
  • failed → HTTP is still 200, not an HTTP error. The failure is nested at data.error (code, type, message, retryable). Detect it with data.status === "failed", not a top-level error. creditsCharged is 0, and meta carries only {requestId, creditsCharged, platforms} — do not read partial, platformResults or warnings on a failed job.

Pace your polling: honour the Retry-After header, back off between attempts, and cap the number of attempts. A tight loop hits 429 rate_limit_exceeded (120 requests/minute).

Known limitations

  • Pagination: limit/cursor are accepted where documented, but availability depends on the endpoint and the upstream source — treat meta.pagination as authoritative and stop when hasMore is false or nextCursor is null.
  • Externally-sourced ids: a Vrbo id obtained somewhere other than /v1/search may not resolve upstream and can produce a failed job (all_actors_failed). Prefer ids from /v1/search (platformListingId).
  • Platform gaps: see the support matrix above — google has no listing or reviews endpoint.

Credits

Number-free by design — failed, empty and blocked calls are never billed, and stay_test_ sandbox calls are always free. Current costs: https://stayingapi.com/pricing · full contract: https://api.stayingapi.com/openapi.json.

Trademark

StayingAPI is an independent service and is not affiliated with, endorsed by, or sponsored by Google Hotels. Google Hotels is a trademark of its respective owner.


Get your free key → https://stayingapi.com/signup · Docs: https://stayingapi.com/docs

Top skills in this category

Gifgrep

@steipete

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

720k

Playwright MCP

@spiceman161

Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.

15946k

Playwright (Automation + MCP + Scraper)

@ivangdavila

Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).

12941k

google-slides

@byungkyu

Google Slides API integration with managed OAuth. Create presentations, add slides, insert content, and manage slide formatting. Use this skill when users want to interact with Google Slides. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login; default to read and list calls, and confirm every write or new connection with the user.

3320k

Scrapling Official Skill

@d4vinci

Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; web_fetch fails; the site has anti-bot protections; write Pyth

2814k