Start free

Platforms MCP server

MCP server · 4 tools · 2 endpoints

Tripadvisor MCP server

Search hotels, restaurants and attractions on Tripadvisor, then read their reviews, through one MCP connection.

Get a free key Connect in a minute

100 credits on signup · No card · Sign in with OAuth or paste a key

scrapersocial-tripadvisor mcp.scrapersocial.com/tripadvisorconnected
you

Find hotels in <city> on Tripadvisor and show the top 10 with their ratings

agent
calls search 3 credits / place
{ "query": "<keywords>" }
server
returns
places [{ … }] · one per place
Shape only. Keys follow the tool's summary; a real call returns the full record. 1 call · 3 credits

Connect

One URL. Your client already knows what to do with it.

The first call opens a sign-in. New accounts get 100 credits, no card. Every client below shares one account and one balance.

Get a free key
server url https://mcp.scrapersocial.com/tripadvisor
claude.aiOAuth

Settings → Connectors → Add custom connector, then paste the server URL.

mcp.scrapersocial.com/tripadvisor

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

$ claude mcp add --transport http scrapersocial-tripadvisor https://mcp.scrapersocial.com/tripadvisor

Approve the sign-in prompt on first use.

Cursorone click

Installs the server and opens the MCP panel.

Add to Cursor
or paste the JSON into .cursor/mcp.json
{ "mcpServers": { "scrapersocial-tripadvisor": { "url": "https://mcp.scrapersocial.com/tripadvisor", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Other clients · VS Code, Windsurf, Gemini CLI, anything that speaks MCP
VS Codeone click or JSON
Add to VS Codeor run MCP: Add Server, choose HTTP and use:
{ "name": "scrapersocial-tripadvisor", "type": "http", "url": "https://mcp.scrapersocial.com/tripadvisor" }
Windsurf~/.codeium/windsurf/mcp_config.json
{ "mcpServers": { "scrapersocial-tripadvisor": { "serverUrl": "https://mcp.scrapersocial.com/tripadvisor", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Gemini CLI~/.gemini/settings.json
{ "mcpServers": { "scrapersocial-tripadvisor": { "httpUrl": "https://mcp.scrapersocial.com/tripadvisor", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Any clientStreamable HTTP · OAuth 2.1 or Bearer
$ npx add-mcp https://mcp.scrapersocial.com/tripadvisor

One account and one balance across every client and the every-platform hub at mcp.scrapersocial.com.

What it does

What your agent can do with Tripadvisor

Is the hotel any good? Tripadvisor holds the longest public answer to that question for almost any property on earth, written by people who stayed there. ScraperSocial’s Tripadvisor spoke gives your agent two tools for reading it: search, which finds hotels, restaurants and attractions by keyword, and get_reviews, which takes a listing URL and pages through its reviews.

That’s the entire surface, and the two cover a lot. Search returns places with their Tripadvisor URLs, so the agent can go from ‘best ramen in Osaka’ to a list of candidates to a stack of reviews in three calls. list_endpoints and call_endpoint are there too, so /v1/tripadvisor/search and /v1/tripadvisor/reviews can be called by path if you prefer.

Tripadvisor is a review site, not a social network; to ScraperSocial it’s public web data, whatever a visitor sees on a listing, as JSON, with no account on either side.

Both endpoints cost 3 credits per item. A search returning 10 places is 30 credits; 50 reviews are 150. Connect https://mcp.scrapersocial.com/tripadvisor and ask about a place by name.

Four jobs it finishes on its own

01

Summarising reviews before a booking decision

Paste a hotel URL and ask for the last 50 reviews grouped by theme. The agent can separate noise complaints from cleanliness ones, and tell you whether the bad reviews cluster in one month.

02

Benchmarking a property you manage

Run `search` for your city and category, pick the competitors, and pull reviews for each. The agent compares ratings and the topics guests raise, which is sharper than a star average.

03

Restaurant and attraction shortlists

Search for a cuisine or an activity in a destination, then read reviews for the top few. It's the research a travel planner does by hand, done in one prompt.

04

Tracking review velocity

Fetch the newest reviews for a listing weekly and record the count and average. A sudden drop is an early warning for a property, a franchise or a client.

Limits · read before you connect

What this does not do

Written by a person, not generated. If something here is wrong, tell us.

Listings and reviews only. There are no room rates, availability, bookings or booking links; the server isn’t a travel API. Owner tools such as responding to reviews or management-centre analytics are not reachable, and the agent never signs in. Reviews cost 3 credits each, so a hotel with thousands of reviews is expensive to read in full; set a limit and sample, or page through with the cursor, fifty at a time. Search is also 3 credits per place returned. A call that finds nothing is charged 1 credit. Responses can be served from cache; fresh: true fetches again at no extra charge.

Tools

4 tools, same names as the every-platform hub

Two do one Tripadvisor thing each. The last two reach all 2 endpoints by path, so nothing in the catalog is out of an agent's reach.

Full credit table →

Search a platform

search

Keyword search over one platform's public content.

3 credits / place

Read reviews

get_reviews

Public reviews and ratings for a product, business, app or company page.

3 credits / review
Reaches every endpoint by path

List every Tripadvisor endpoint

list_endpoints

Browse every Tripadvisor endpoint, its input and its credit cost. Free, and calls nothing upstream.

free

Call any Tripadvisor endpoint by path

call_endpoint

Run any Tripadvisor endpoint by its path, so nothing Tripadvisor offers is out of reach of an agent.

endpoint's own cost

Pricing

100 free credits is 33 search results.

Then $5 a month for 1,000 credits, or $4 per 1,000 as a top-up. No card to start. Every call costs 3 credits.

33 search resultssearch · 3 each
Get a free key 100 credits on signup · $5 for 1,000 · full credit table

Prompts

Things to ask once it is connected

Copy one, swap the placeholder, paste it into your client.

Find hotels in <city> on Tripadvisor and show the top 10 with their ratings

Summarise the last 50 reviews for <tripadvisor listing url> by theme

Search Tripadvisor for <restaurant name> in <city> and pull 20 reviews

Compare <tripadvisor url 1> and <tripadvisor url 2> on rating and the complaints guests raise

What do reviewers say about breakfast at <tripadvisor hotel url>?

Questions

Before you connect

How much does it cost to read a hotel's reviews? #

3 credits per review. Fifty reviews are 150 credits; 1,000 credits are $5. Every new account starts with 100 free credits, which covers a search and about 30 reviews.

Can I get prices or check availability? #

No. The server returns what the listing page shows, and pricing and availability aren't part of that. Use a booking engine for rates.

Is ScraperSocial affiliated with Tripadvisor? #

It is not. ScraperSocial is an independent service and this isn't an official Tripadvisor API. It reads public listing pages only.

What input does each tool need? #

`search` takes a text query. `get_reviews` takes the listing's Tripadvisor URL. Search results include URLs, so the agent can chain them.

Does it cover restaurants and attractions as well as hotels? #

Yes. Search returns places of any type Tripadvisor lists, and reviews work on any listing URL.