Scope a new market before you commit to it
Market research is the work that never gets done, because it costs a week of somebody senior and by the time it lands the market has moved. With the Veetal MCP connected, the same question takes one prompt: your assistant pulls live supply and pricing for any destination and writes up what it means.

What you'll build
A written market briefing for any destination: how much supply there is and of what kind, where the price bands sit by star category, how the scores distribute, which properties anchor the top of the market and where the gap is — plus the questions the data raises that you should answer before investing.
Set this up first
RequiredThe endpoints don't take free text — they take your identifiers. This recipe assumes the things below already exist on your account; while one of them is missing, the call answers with an error or with less than you expect. Each point links to the recipe that walks it.
- 01
Create the location search
A destination plus its filters — stars, board, distance, occupancy. Those filters are the entity: they decide which hotels the market covers and what every run costs.
Guide: Register the four entity types on your account →
How it works
- 01
Connect the MCP
One line of configuration in Claude or Cursor and your assistant can reach your Veetal account. The setup page walks it through. Then create a location search for the city in the dashboard, with accommodation type Hotel and no star filter: the assistant splits by category itself, and hotels alone usually stay under Booking.com's 1,000-result cap, where hotels plus apartments would not.
- 02
Ask in your own words
No endpoint names, no parameters. Describe the market and the decision you are weighing; the assistant picks the calls.
- 03
Push back on the answer
The value is in the second question. Ask it to separate hotels from apartments, to redo the bands excluding the outliers, to tell you what it cannot know from this data.
The call
Under the hood the assistant runs live location searches. This is the same call, by hand, if you would rather see it than ask for it.
curl "https://api.veetal.app/v3/real-time/location-search/YOUR_LOCATION_SEARCH_ID/booking/2027-03-16" \
-H "veetal-api-key: YOUR_API_KEY"Build it with AI
Connect the MCP →Paste this prompt into an assistant with the Veetal MCP connected and it builds the whole app against your data — no front-end work.
Using my Veetal Connect data, scope Porto as a destination I do not operate in yet.
I run four-star city hotels and I am deciding whether to look for a building there.
Use my location search for Porto. Before you run anything, tell me its filters and what
the searches will cost, and wait for my OK.
Pull live availability and pricing for three dates that are not all the same kind of
day — a midweek night in low season, a weekend in high season, and a date during a
major local event only if you can name it and say where that comes from — if you
cannot, say so and use a second high-season date instead.
For each date tell me:
- how much supply is listed, split by star category (and by accommodation type if my
location search includes more than hotels) — give me `total` and say whether
coverage.truncated is true: above 1,000 results the list is a sample, not the supply
- the price bands: median and the 25th/75th percentiles per category, not just an average
- how review scores distribute, and whether the expensive properties are also the
best-reviewed or whether there is a gap someone could walk into
- the five properties anchoring the top of the market, with what they charge and score
Leave properties with no reviews (score 0) out of the score statistics and the top five:
an unrated property is not a benchmark.
Then, in plain prose: where is the gap, what would a new four-star need to charge to be
credible, and what does this data NOT tell me that I should find out before committing
capital. Be concrete and tell me your uncertainty — I would rather hear "the sample is
thin for five-star" than a confident number you cannot support.Questions
Does this cost credits?
Yes. Each date is one live search on Booking.com at 9.84 credits, so the three dates in the prompt cost about 30 credits and comparing three cities about 90. Errors are not charged and a cached answer costs nothing. The prompt asks the assistant to state the cost before it runs anything.
How current is the data?
It is fetched when you ask, unless the same search ran moments before and the answer comes from cache (free; ask for fresh data if you need it). That is the point of the Real Time family: no import to schedule, no waiting for tomorrow's run.
Can it compare several cities?
Yes, and that is where it earns its keep — the same question asked of three candidate destinations, answered in the same shape, is a decision document. Each city needs its own location search.
What will it get wrong?
It sees what the OTA lists for the dates you name. A shoulder-season Tuesday is not the market; ask for several dates before you conclude anything about a destination's price level.
Build your own
Start free with 1,000 API credits. No credit card, no sales call.
What do you want to build with booking location listing?
Say it in one line and we hand you back the prompt, the recipe if one already exists, and the APIs it runs on — starting with booking location listing.