MCP + API · kestrel/tripadvisor-restaurant-reviews
TripAdvisor Restaurant Reviews Scraper — Diner Reviews, Ratings
TripAdvisor restaurant reviews and attraction reviews by URL or name. One row per review: bubbles, text, food, service, value, atmosphere ratings, visit date, diner tips, photos, owner reply. Free location row: rating, review count, cuisine, menu, hours. Filters: negative reviews, new reviews only.
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/tripadvisor-restaurant-reviews
Generic MCP client configuration
{
"mcpServers": {
"kestrel-tripadvisor-restaurant-reviews": {
"url": "https://mcp.apify.com?tools=call-actor,fetch-actor-details,kestrel/tripadvisor-restaurant-reviews"
}
}
}
Understand the output before you run
One row per diner or visitor review (charged), plus a free location context row and a free status row per location and language.
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 71 declared output fields
| Field | Type | Meaning |
|---|---|---|
type | string | review | location | status |
target | string / null | The input value (URL, id or name) this row came from |
location_id | string / null | TripAdvisor's numeric location id (the d<number> in its URLs) |
geo_id | string / null | TripAdvisor's numeric geo id of the city (the g<number> in its URLs) |
location_name | string / null | Restaurant or attraction name as the review page shows it |
location_type | string / null | restaurant | attraction (what TripAdvisor's own placeType says the location is) |
language | string / null | Site language the row was read in (en = tripadvisor.com, de = tripadvisor.de, …) |
review_id | string / null | TripAdvisor's numeric review id |
original_language | string / null | Language the review was written in |
translated | boolean / null | true when the text is a machine translation into the site language |
title | string / null | Review title |
text | string / null | Full review text |
rating | number / null | 1-5 bubbles on review rows; the location's overall bubble rating (e.g. 4.3) on location rows |
sub_ratings | object / null | On a restaurant review, the bubbles the diner gave for food, service, value and atmosphere; on a location row the averages of the same four. Attractions carry none |
review_date | string / null | Publication date, YYYY-MM-DD |
created_date | string / null | Date the review was written, YYYY-MM-DD |
visit_date | string / null | Month of the visit as TripAdvisor records it, YYYY-MM-DD |
trip_type | string / null | FAMILY | COUPLES | SOLO | BUSINESS | FRIENDS | null |
tips | array / null | The diner's short tips for the next guest ("ask for the terrace"), when the review carries any |
helpful_votes | integer / null | Helpful votes the review received |
reviewer_name | string / null | Reviewer display name |
reviewer_username | string / null | Reviewer profile handle |
reviewer_verified | boolean / null | Whether TripAdvisor marks the reviewer as verified |
reviewer_contributions | integer / null | Reviewer's total contributions on TripAdvisor |
reviewer_helpful_votes | integer / null | Helpful votes across all of the reviewer's contributions |
reviewer_hometown | string / null | Reviewer hometown as shown, e.g. "Brooklyn, New York" |
photos | array / null | Photo URLs attached to the review (1200 px renditions) |
photo_count | integer / null | How many photos the review carries |
response | string / null | The owner's or manager's reply text, if any |
response_date | string / null | Date of the owner reply, YYYY-MM-DD |
response_id | string / null | TripAdvisor's id of the owner reply |
url | string / null | Direct URL of the review (review rows) or of the location's review page (location rows) |
location_url | string / null | The location's canonical review page on the site the row was read from |
review_count | integer / null | Total reviews the location has across all languages |
rating_counts | object / null | Reviews per bubble rating, keys "1"…"5" |
reviews_by_language | object / null | Reviews per language, e.g. {"en": 4686, "pt": 2865} |
ranking | string / null | TripAdvisor ranking sentence, e.g. "#735 of 6,596 Restaurants in Lisbon" |
ranking_position | integer / null | Rank position in the city |
ranking_of | integer / null | How many locations of this kind are ranked in the city |
ranking_category | string / null | What the ranking counts, e.g. "Restaurants in Lisbon" or "things to do in Lisbon" |
cuisines | array / null | Cuisines TripAdvisor lists for the restaurant, e.g. ["Portuguese", "Seafood"] |
price_range | string / null | TripAdvisor price band, e.g. "$$ - $$$" |
category_tags | array / null | Attraction categories, e.g. ["Points of Interest & Landmarks", "Cooking Classes"] |
dish_tags | array / null | The dish and topic keywords TripAdvisor mines from the reviews ("clams", "tiger prawns", "worth the wait") |
address | string / null | Street address |
city | string / null | City |
state | string / null | State or region, where TripAdvisor lists one |
postal_code | string / null | Postal code |
country_code | string / null | ISO country code |
latitude | number / null | Latitude |
longitude | number / null | Longitude |
phone | string / null | Phone as listed |
email | string / null | Contact e-mail as listed |
website | string / null | Official website as listed |
menu_url | string / null | Menu link TripAdvisor points at |
accepts_reservations | boolean / null | Whether TripAdvisor marks the restaurant as taking reservations |
open_now | boolean / null | Whether TripAdvisor rendered the location as open at the time of the request |
hours | array / null | Opening hours as sentences, e.g. ["Sunday 12:00-23:00"] |
permanently_closed | boolean / null | true when TripAdvisor marks the location as closed |
description | string / null | The location's own description, when TripAdvisor has one |
neighborhoods | array / null | Neighbourhood names TripAdvisor places the location in |
reviews_listed | integer / null | Reviews the site lists for the location in this language (translations included) |
reviews_fetched | integer / null | Reviews read in this run for the location and language before filters |
status | string / null | ok | no_reviews | not_found | wrong_type | duplicate | error (status rows) |
reviews | integer / null | Reviews delivered for this location and language (status rows) |
filtered | integer / null | Reviews dropped by the filters, never charged (status rows) |
pages | integer / null | Review pages read (status rows) |
total | integer / null | Reviews the site lists in this language (status rows) |
duplicates | integer / null | 1 when this target resolved to a location another target already covers (status rows) |
error | string / null | Why a target failed, or what it turned out to be (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 1.2.5; it is not a promise that the source has matching rows today.
{
"actor": "kestrel/tripadvisor-restaurant-reviews",
"input": {
"startUrls": [
"https://www.tripadvisor.com/Restaurant_Review-g189158-d2703366-Reviews-Cervejaria_Ramiro-Lisbon_Lisbon_District_Central_Portugal.html"
],
"locationType": "any",
"languages": [
"en"
],
"maxReviewsPerLocation": 3
},
"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 |
|---|---|---|
review | $0.005 | One TripAdvisor restaurant or attraction review: 1-5 bubbles, food/service/value/atmosphere sub-ratings, tips, owner's reply (row keys review_id, rating, title, text, sub_ratings, language, original_language, visit_date, trip_type, tips, reviewer_name, photos, helpful_votes, response): $5 per 1,000 reviews, once per language site. Not charged: the location row (rating, ranking, cuisine, hours, address, phone), reviews removed by maxRating, tripTypes, sinceDate, requireText or includeTranslated, locations with no reviews, unknown ids, hotel ids (wrong_type), duplicate targets, failed pages and 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 when starting it (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: 1.2.5. Refresh live details before a large or recurring run.