Tripadvisor Attractions MCP Server
Pricing
Pay per event + usage
Tripadvisor Attractions MCP Server
Tripadvisor Attractions MCP Server for AI agents. Give Claude, Cursor or ChatGPT live tools to search destinations, list a city's top things to do, and fetch attraction details — ratings, reviews, categories, GPS. Also runs as a classic scraper. Pay per tool call.
Pricing
Pay per event + usage
Rating
0.0
(0)
Developer
axly
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
2 days ago
Last modified
Categories
Share
Give your AI assistant live access to Tripadvisor attractions. This actor runs as a Model Context Protocol (MCP) server so agents like Claude, Cursor, ChatGPT and n8n can search destinations, list a city's top things to do, and fetch attraction details on demand — and it also works as a classic one-shot scraper.
Built on Tripadvisor's mobile API (static key, no DataDome), so tool calls stay reliable.
Who uses this
- AI agent / app builders — add real Tripadvisor data to a chatbot, trip planner or research agent without maintaining a scraper.
- Analysts & researchers — query attractions ad hoc from an assistant.
- Travel product teams — prototype destination features with live data.
MCP tools
| Tool | What it does |
|---|---|
search_tripadvisor_geos | Resolve free text to Tripadvisor destinations (geo id, name, type, route). |
list_attractions | Ranked things to do for a city/geo — rating, reviews, category, GPS, photo. |
get_attraction | Detail for one attraction — rating, reviews, canonical tripadvisor.com URL. |
Connect it
Start the actor in Standby mode and point your MCP client at:
https://<your-actor-standby-url>/mcp
Example (Claude Desktop / Cursor config):
{"mcpServers": {"tripadvisor": {"url": "https://<your-actor-standby-url>/mcp"}}}
Then ask your agent things like "List the top 10 things to do in Rome with their ratings and coordinates" or "Find the Tripadvisor geo id for Kyoto".
Classic scraper mode
Prefer a one-shot dataset run? Provide query (a city name or geo id) and the
actor pushes that city's attractions to the dataset — handy for scheduled jobs.
Output fields (list_attractions / dataset)
| Field | Type | Description |
|---|---|---|
location_id | integer | Tripadvisor attraction id |
name | string | Attraction name |
rank | integer | Ranked position in the city |
rating | number | Average bubble rating (0–5) |
review_count | integer | Traveler reviews |
category | string | Attraction category |
latitude | number | GPS latitude |
longitude | number | GPS longitude |
image_url | string | Primary photo URL |
geo_id | integer | City/region geo id |
geo_name | string | City/region name |
Example (classic run) input
{ "query": "Paris", "limit": 20, "includeCoordinates": true }
FAQ
How do agents use it? Start it in Standby mode and connect any MCP client to
/mcp (Streamable HTTP). The three tools appear automatically.
Where does the data come from? Tripadvisor's mobile app API — the same data the app shows for a destination's "Things to Do".
Is it reliable? The mobile API is not behind the website's DataDome challenge, so tool calls are stable.
Is scraping this legal? You are responsible for complying with Tripadvisor's terms and applicable laws; use only public data and reasonable rates.