# Arcadium Data Scrapers MCP Server (`arcadium/scrapers-mcp`) Actor MCP server for AI agents: live reviews (Tripadvisor, Booking.com, Trustpilot, Yelp, apps), hotel prices, Amazon, Etsy, 1688, TikTok Shop, Zillow, jobs, YouTube. From $0.30 per 1,000 results, billed on your Apify account; also Google Trends, news and used cars. No personal data. - **URL**: https://apify.com/arcadium/scrapers-mcp.md - **Developed by:** [Arcadium Data](https://apify.com/arcadium) (community) - **Categories:** MCP servers, AI, Agents - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing Pay per usage This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ## Arcadium Data Scrapers MCP Server A remote MCP server that gives Claude, Cursor, LangChain and other AI agents live web data: **reviews** (Tripadvisor, Booking.com, Google Hotels, Agoda, Trip.com, Yelp, Trustpilot, Capterra, TrustRadius, Google Play, App Store) and **review monitoring**, **hotel prices** (Google Hotels, Booking.com), **Amazon** search and Best Sellers, **Etsy**, **1688.com** factory prices, **TikTok Shop**, **Zillow** homes, **Google Trends**, **Google News**, **YouTube** transcripts and video lists, **company hiring** signals, **job search**, **software products** (Capterra) and **used cars** in 8 EU countries (AutoScout24). Each tool call runs one Arcadium Data scraper on your own Apify account and is billed there per result, from $0.30 per 1,000 results. The server itself is free. Answers are compact JSON with no reviewer, recruiter or seller names. - Endpoint: `https://arcadium--scrapers-mcp.apify.actor/mcp` (Streamable HTTP, on Apify) - Auth: your Apify API token on every request, `Authorization: Bearer ` ([get a token](#get-a-token)) - Server card: `/.well-known/mcp/server-card.json` (also at `/mcp/server-card`) - Every call returns at most 50 rows and has a spend cap of $0.10-0.50; all rows stay in the run's dataset on your account (`datasetUrl` in every answer) ### Connect #### Claude Code ```sh claude mcp add --transport http arcadium-scrapers https://arcadium--scrapers-mcp.apify.actor/mcp \ --header "Authorization: Bearer $APIFY_TOKEN" ``` #### Claude Desktop In `claude_desktop_config.json`, through the `mcp-remote` bridge (it adds the bearer header): ```json { "mcpServers": { "arcadium-scrapers": { "command": "npx", "args": [ "-y", "mcp-remote", "https://arcadium--scrapers-mcp.apify.actor/mcp", "--header", "Authorization: Bearer ${APIFY_TOKEN}" ], "env": { "APIFY_TOKEN": "" } } } } ``` #### Cursor `~/.cursor/mcp.json` (or `.cursor/mcp.json` in a project): ```json { "mcpServers": { "arcadium-scrapers": { "url": "https://arcadium--scrapers-mcp.apify.actor/mcp", "headers": { "Authorization": "Bearer " } } } } ``` #### LangChain / LangGraph (Python) ```python from langchain_mcp_adapters.client import MultiServerMCPClient client = MultiServerMCPClient({ "arcadium-scrapers": { "transport": "streamable_http", "url": "https://arcadium--scrapers-mcp.apify.actor/mcp", "headers": {"Authorization": f"Bearer {APIFY_TOKEN}"}, } }) tools = await client.get_tools() # pass to create_react_agent(model, tools) ``` Any other MCP client: Streamable HTTP, URL above, bearer header. ### Pricing and tools One tool per question an agent asks, each with a small input schema, an example and its price in the description. We chose this over one generic "run any scraper" tool: with a generic tool the agent has to pick an actor id and write that actor's full input without seeing its schema, which is where tool calls tend to go wrong. A named tool puts the question, the schema and an example in front of the agent before it calls. | Tool | Question it answers | Runs (Apify Store) | Price per 1,000 | |---|---|---|---| | `search_reviews` | What do recent reviews say about this hotel, restaurant or place? Review page URL or a name with its city | `arcadium/tripadvisor-reviews`, `arcadium/booking-reviews`, `arcadium/google-hotel-reviews`, `arcadium/agoda-tripcom-reviews`, `arcadium/yelp-reviews` | $0.30-5.40 reviews | | `software_reviews` | What do users say about this software product or app? Name or Capterra / TrustRadius / Google Play / App Store link | `arcadium/software-reviews`, `arcadium/capterra-reviews`, `arcadium/trustradius-reviews` | $1.79-3.59 reviews | | `hotel_reviews_all_sites` | How is one hotel rated on Tripadvisor, Booking.com, Google, Agoda and Trip.com, on one 1-5 scale? | `arcadium/hotel-reputation` | $4.50 reviews (summary free) | | `review_monitor` | Which new negative reviews and rating moves since my last check? Stateful watchlist on your account | `arcadium/reputation-monitor` | $12.00 entity checks, $2.00 alerts, $9.00 first-run baselines | | `hotel_prices` | What does a hotel cost on these dates? City search or named hotels, cheapest booking sites (Google Hotels) | `arcadium/google-hotels` | $4.49 hotels, $0.90 offers | | `trends` | How does search interest compare over time, and what is rising? (Google Trends) | `arcadium/google-trends` | $2.70 keywords | | `news` | What is the news on this topic or company? (Google News) | `arcadium/google-news` | $3.60 articles | | `youtube_transcript` | What is said in this YouTube video? | `arcadium/youtube-transcripts` | $2.48 transcripts | | `youtube_videos` | What did this YouTube channel publish, or what ranks for this search? | `arcadium/youtube-videos` | $3.60 videos | | `company_hiring` | Which ATS does this company use, and how much is it hiring? | `arcadium/ats-lookup` | $4.00 companies | | `job_search` | Which jobs are open at these companies (any country), or for this keyword in Australia / New Zealand (Seek)? | `arcadium/career-site-jobs`, `arcadium/seek-jobs` | $1.80 jobs | | `software_products` | Which products lead this software category, at what price and with which features? (Capterra) | `arcadium/capterra-products` | $6.21 products | | `used_cars` | Which used cars are for sale in DE, AT, BE, ES, FR, IT, LU, NL, and is the price good? (AutoScout24) | `arcadium/eu-car-listings` | $0.44 cars ($0.89 with details) | | `trustpilot_reviews` | What do customers say about this company or online shop on Trustpilot? | `arcadium/trustpilot-reviews` | $0.52 reviews (company rows free) | | `trustpilot_companies` | Which companies does Trustpilot list in this category and country, and how are they rated? | `arcadium/trustpilot-reviews` | $2.00 companies | | `amazon_search` | What sells on Amazon for this keyword, at what price? 21 Amazon stores | `arcadium/amazon-products` | $0.54 results | | `amazon_bestsellers` | What ranks top in this Amazon category (Best Sellers, New Releases, Movers & Shakers, ...)? | `arcadium/amazon-products` | $5.31 ranks | | `marketplace_china` | What does this product cost at the factory in China? (1688.com) | `arcadium/1688-products` | $1.80 products ($4.49 with details) | | `etsy_listings` | What sells on Etsy for this keyword, and at what price? | `arcadium/etsy-products` | $7.20 listings | | `booking_prices` | What does a hotel cost on Booking.com on these dates, and did the price change? | `arcadium/booking-prices` | $2.70 hotel stays | | `tiktok_shop` | What sells on TikTok Shop (US, GB), at what price and how many sold? | `arcadium/tiktok-shop-products` | $22.50 products ($7.50 store card only) | | `zillow_homes` | Which homes are for sale, for rent or recently sold in this US area, and at what price? (Zillow) | `arcadium/zillow-properties` | $2.10 homes ($3.20 with details) | | `get_run_results` | Results of a call that answered `"status": "running"` (free, no new run) | none | free | Prices are the Apify free-plan prices per result; paid Apify plans pay the same or less. Error rows (not found, blocked, invalid input) are always free. Annotations: every scraping tool is `readOnlyHint: true`, `openWorldHint: true`, `idempotentHint: false` (each call is a new billed run); `review_monitor` and the tools with a watch mode (`trustpilot_reviews`, `trustpilot_companies`, `amazon_search`, `amazon_bestsellers`, `booking_prices`) are `readOnlyHint: false` because they keep state in a key-value store on your account; `get_run_results` is read-only and idempotent. ### Answers **Output example** (every tool answers with this envelope; illustrative values, rows shortened): ```json { "tool": "trends", "source": "arcadium/google-trends", "status": "done", "count": 1, "results": [{ "keyword": "claude", "averageInterest": 41, "interestOverTime": [["Oct 2026", 63]] }], "errors": [], "run": { "runId": "aBcD1234efGh5678", "status": "SUCCEEDED", "chargedEvents": { "result": 1 }, "chargedUsd": 0.0027 }, "totalRows": 1, "datasetId": "xYz123", "datasetUrl": "https://api.apify.com/v2/datasets/xYz123/items?clean=true&format=json" } ``` - `results`: compact rows (only the useful fields, no empty values, long texts cut). - `errors`: free error rows with `code` (`no_match`, `blocked`, `invalid_input`, ...) and `message`. - `status: "running"`: the run is still going; call `get_run_results` with the `runId` and the same tool name. - `datasetUrl`: all rows of the run, read with your Apify token. ### Related actors - [Tripadvisor Reviews Scraper: Ratings, Replies, Translations](https://apify.com/arcadium/tripadvisor-reviews) - [Google Hotels Scraper: Prices, Ratings, Booking Offers](https://apify.com/arcadium/google-hotels) - [Google Trends Scraper: Interest, Related Queries, Trending](https://apify.com/arcadium/google-trends) - [YouTube Transcript & Subtitles Scraper: Text, SRT, VTT](https://apify.com/arcadium/youtube-transcripts) ### Limitations At most 3 runs in flight and 120 calls an hour per token, 50 rows per answer, and a spend cap on every run ($0.10-0.50, set per tool). ### Get a token - Apify account (free tier included): Console > Settings > API & Integrations, https://console.apify.com/settings/integrations - No account: mint a prepaid, capped token with x402 or MPP at https://agi.apify.com ### Privacy Public data only, no login. Reviewer, recruiter and seller names, emails and phone numbers are never returned. The server stores no tool inputs, tokens or IP addresses; it logs one row per call (tool, channel, status, USD) for usage statistics. # Actor input Schema ## `waitSecs` (type: `integer`): How long a tool waits for its scraper run before answering with status "running" and a runId to poll with get_run_results, 30 to 280 seconds. ## Actor input object example ```json { "waitSecs": 150 } ``` # Actor output Schema ## `mcp` (type: `string`): Streamable HTTP endpoint of this server run; clients normally use the Standby URL + /mcp instead. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "waitSecs": 150 }; // Run the Actor and wait for it to finish const run = await client.actor("arcadium/scrapers-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "waitSecs": 150 } # Run the Actor and wait for it to finish run = client.actor("arcadium/scrapers-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "waitSecs": 150 }' | apify call arcadium/scrapers-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,arcadium/scrapers-mcp" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/k6fXXkd2KD3Gg9u6G/builds/6fzWVJsBWFe5ASyjd/openapi.json