MCP + API · kestrel/despegar-hotel-ratings
Despegar Hotel Ratings Scraper - Guest Scores, AI Summary
Get Despegar hotel ratings by hotel URL or ID in Latin America. One row per hotel: guest score, review count, six category scores, stars, city and Despegar AI review summary. Free: up to four published comments, not a full review list. Filter minimum rating. Opiniones y calificaciones de hoteles.
Open Actor Download MCP config
Connect this tool
Add this URL as a remote MCP server in your client, then sign in to Apify. For a client-specific setup, use Apify's configurator.
https://mcp.apify.com?tools=call-actor,fetch-actor-details,kestrel/despegar-hotel-ratings
Generic MCP client configuration
{
"mcpServers": {
"kestrel-despegar-hotel-ratings": {
"url": "https://mcp.apify.com?tools=call-actor,fetch-actor-details,kestrel/despegar-hotel-ratings"
}
}
}
Understand the output before you run
One row per hotel with its guest rating, category scores and Despegar's own AI summary (charged), plus the up-to-four published comments and a status row per target (both free).
Declared dataset fields and row types · Output locations and dataset links
Use the declared dataset schema for item fields; the output schema describes where results are stored. Optional fields may be null or absent. If an integration shows a sampled schema without an optional field, check this declaration, the Actor instructions and actual returned rows before concluding that the field is unsupported.
Inspect 52 declared output fields
| Field | Type | Meaning |
|---|---|---|
type | string | hotel | review | status |
target | string / null | The input value (URL or hotel id) this row came from |
hotel_id | string / null | Despegar's numeric hotel id (the number in /h-<id>/); the same id on every Despegar country domain |
hotel_name | string / null | Hotel name as the chosen Despegar site writes it |
hotel_url | string / null | Canonical hotel page URL on the domain that was read |
city | string / null | City, from the location line under the hotel name (hotel rows) |
country | string / null | Country of the hotel, in the page's language (hotel rows) |
address | string / null | Street address as printed in the map section (hotel rows) |
latitude | number / null | Latitude of the hotel marker (hotel rows) |
longitude | number / null | Longitude of the hotel marker (hotel rows) |
stars | integer / null | Star rating, counted from the stars printed above the hotel name (hotel rows) |
rating | number / null | Overall guest rating on Despegar's 0-10 scale, e.g. 8.4 |
rating_scale | integer / null | The scale the rating is on: always 10 (hotel rows) |
rating_5 | number / null | The same score converted to the 0-5 star scale, e.g. 8.4 -> 4.2 |
rating_label | string / null | Despegar's word for the score, e.g. "Muy bueno" / "Very good" (hotel rows) |
review_count | integer / null | How many guest reviews the rating is based on, as Despegar counts them (e.g. 4511) — not how many this actor can deliver (hotel rows) |
reviews_shown | integer / null | How many individual comments the page actually publishes: at most four (hotel rows) |
score_service | number / null | Category score 0-10: services and installations (hotel rows) |
score_staff | number / null | Category score 0-10: accommodation staff (hotel rows) |
score_location | number / null | Category score 0-10: location (hotel rows) |
score_internet | number / null | Category score 0-10: internet / Wi-Fi (hotel rows) |
score_cleanliness | number / null | Category score 0-10: cleaning (hotel rows) |
score_value | number / null | Category score 0-10: price/quality (hotel rows) |
category_scores | object / null | The same six scores keyed by Despegar's own codes: service, servicePersonal, location, internetAccessAndQuality, cleaning, qualityprice (hotel rows) |
summary | string / null | Despegar's own AI-written summary of what guests say about the hotel, generated by Despegar from all its reviews and published on the page — their text, not ours (hotel rows) |
verified_note | string / null | Despegar's provenance note for the sample, e.g. "Clientes verificados por Grupo Despegar." (hotel rows) |
providers | array / null | Which review providers the published comments come from; DESPEGAR on every hotel we have seen (hotel rows) |
trip_types | array / null | Traveller profiles Despegar offers to filter the comments by: couple, friends, singles, family (hotel rows) |
page_language | string / null | Language the domain served, e.g. es or en (hotel rows) |
page_country | string / null | Country code of the Despegar site that was read, e.g. AR (hotel rows) |
review_id | string / null | Despegar's id for the comment (review rows) |
review_date | string / null | The month the guest wrote the comment, in the page's language, e.g. "Agosto 2023" — Despegar publishes no day (review rows) |
review_month | string / null | The same date normalised to YYYY-MM (review rows) |
text | string / null | The comment: the good half and the bad half joined; Despegar reviews have no title (review rows) |
good | string / null | What the guest liked (review rows) |
bad | string / null | What the guest disliked; absent when they only wrote praise (review rows) |
reviewer | string / null | Guest's first name, when they published one (review rows) |
reviewer_country | string / null | Guest's country, when published (review rows) |
reviewer_country_code | string / null | Two-letter code for that country (review rows) |
trip_type | string / null | Who was travelling: couple | friends | singles | family (review rows) |
trip_type_label | string / null | The same, as the page words it, e.g. "En familia" (review rows) |
language | string / null | Language the comment was written in (review rows) |
provider | string / null | Which provider supplied the comment, e.g. DESPEGAR (review rows) |
provider_label | string / null | Despegar's badge for that provider, e.g. "Huésped verificado" (review rows) |
helpful_votes | integer / null | How many readers marked the comment useful (review rows) |
status | string / null | ok | no_reviews | not_found | filtered | duplicate | blocked | limited | error (status rows) |
hotels | integer / null | 1 when a hotel row was delivered and charged for this target (status rows) |
comments | integer / null | How many published comments were delivered for this target, free (status rows) |
filtered | integer / null | 1 when minRating dropped this hotel before billing (status rows) |
duplicates | integer / null | 1 when this target is the same hotel as an earlier one (status rows) |
error | string / null | Why a target produced nothing (status rows) |
fetched_at | string / null | UTC timestamp of the request |
Start with a small sample
Use call-actor with the JSON below. The $0.25 run ceiling is separate from the Actor input and may stop the sample early. Change the target to match your request. This input validates against build 1.0.8; it is not a promise that the source has matching rows today.
{
"actor": "kestrel/despegar-hotel-ratings",
"input": {
"startUrls": [
"https://www.despegar.com.ar/hoteles/h-265543/riu-cancun"
],
"country": "ar",
"includeComments": true
},
"callOptions": {
"maxTotalChargeUsd": 0.25,
"timeout": 300
},
"waitSecs": 30
}
After completion, use get-dataset-items with storages.datasets.default.id. If still running, poll get-actor-run using the returned runId. Check status rows and errors before treating an empty dataset as no matches.
Call from Python, JavaScript or REST
Python SDK 3 example · JavaScript SDK 2 example · curl + jq example. Each uses this same small input, reads APIFY_TOKEN from your environment, sets a five-minute run timeout and exports all dataset row types as JSON Lines. The $0.25 run ceiling is separate from the Actor input and may stop the sample early. Inspect the run and source status before treating results as complete. Installation and usage.
Pricing and limits
Current listed event prices in USD. Some Actors charge for successful source checks even when no output rows match. The event descriptions below define those differences.
| Event | USD each | What is charged |
|---|---|---|
hotel | $0.004 | One Despegar hotel: the 0-10 guest rating with its review count, six category scores (service, staff, location, Wi-Fi, cleanliness, value), Despegar's AI summary of what guests say, stars, city, country and coordinates (row keys hotel_id, rating, review_count, score_service, score_staff, score_location, score_internet, score_cleanliness, score_value, summary, stars, city, country, latitude, longitude): $4 per 1,000 hotels. Free: the up-to-four comments the page publishes (whatever the review count says; there is no full review list), hotels with no rating, unknown ids, hotels below minRating, duplicates, status rows. No start fee; proxy and compute are included in the event price. The run stops at the maximum cost per run you set (Apify run option maxTotalChargeUsd), never above it. |
Contracts for agents
- Input schema and sample input
- Prepared MCP call and pricing events
- Full Actor instructions and limits
- REST API
Public contract checked 2026-11-11. Active build: 1.0.8. Refresh live details before a large or recurring run.