MCP + API · kestrel/airbnb-reviews-scraper
Airbnb Reviews Scraper — Guest Reviews, Ratings & Host Replies
Airbnb vacation rental guest reviews by URL, id or place. One row per review: rating, text, host replies, translation, language, date, reviewer, location. Lowest rated first and minRating keep only negative reviews (complaints) and bill only those. For sentiment, reputation, competitor research.
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/airbnb-reviews-scraper
Generic MCP client configuration
{
"mcpServers": {
"kestrel-airbnb-reviews-scraper": {
"url": "https://mcp.apify.com?tools=call-actor,fetch-actor-details,kestrel/airbnb-reviews-scraper"
}
}
}
Understand the output before you run
Three row types share one dataset: review (one guest review, charged), listing (context for a listing, free) and status (per listing or place, 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 31 declared output fields
| Field | Type | Meaning |
|---|---|---|
type | string | Row type: review, listing or status. |
id | string / null | Airbnb listing id the row belongs to. |
url | string / null | Listing URL. |
name | string / null | Listing title, when known. |
reviews_total | integer / null | How many reviews Airbnb reports for the listing. |
reviews_fetched | integer / null | Listing rows: how many reviews were fetched for it. |
locale | string / null | Language requested for translations. |
review_id | string / null | Airbnb's id for the review. |
rating | string / integer / null | Star rating the guest gave, 1-5. |
text | string / null | The review as written, in its original language. |
text_localized | string / null | Airbnb's translation into the requested language, when it differs. |
language | string / null | Language the review was written in. |
created_at | string / null | When the review was posted (UTC). |
date_label | string / null | Date as Airbnb shows it, e.g. "1 week ago". |
reviewer_name | string / null | Reviewer's first name. |
reviewer_id | string / null | Reviewer's Airbnb id. |
reviewer_location | string / null | Where the reviewer says they are from. |
reviewer_is_superhost | boolean / null | Whether the reviewer is themselves a Superhost. |
host_reply | string / null | The host's public reply, when there is one. |
host_reply_date | string / null | When the host replied. |
highlight | string / null | The sentence Airbnb highlights from the review. |
stay_type | string / null | Airbnb's tag for the stay, e.g. a group or family trip. |
status | string / null | Status rows: ok, unknown_area, no_results or error. |
listings | integer / null | Status rows: listings harvested. |
reviews | integer / null | Status rows: review rows delivered. |
filtered | integer / null | Status rows: reviews dropped by the rating filter, never charged. |
duplicates | integer / null | Status rows: listings already harvested by another input. |
listing_id | string / null | Status rows: the listing this job was for. |
query | string / null | Status rows: the place searched. |
error | string / null | Status rows: why the job failed, null when it did not. |
fetched_at | string / null | UTC timestamp when the row was fetched. |
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 1.2.6; it is not a promise that the source has matching rows today.
{
"actor": "kestrel/airbnb-reviews-scraper",
"input": {
"locationQueries": [
"Lisbon, Portugal"
],
"maxListingsPerQuery": 3,
"maxReviewsPerListing": 3,
"reviewsSort": "most_recent"
},
"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 guest review with star rating, text, Airbnb's translation and original language, date, reviewer, location, stay type and the host's reply (row keys id, url, name, review_id, rating, text, text_localized, language, created_at, date_label, reviewer_name, reviewer_location, stay_type, host_reply, host_reply_date, reviews_total): $5 per 1,000 reviews, billed once per review per run. Not charged: reviews minRating removes (a 441-review listing returned 4 rows under minRating 3), listing rows, status rows, listings with no reviews, unknown places, failed listings. 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). |
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: 1.2.6. Refresh live details before a large or recurring run.