The Mine Works

Scrape SEC EDGAR filings (10-K, 10-Q, 8-K, S-1, Form 4) as clean JSON with XBRL financials & RAG ready text. Ticker to CIK auto resolve, no API key. Use in Claude, ChatGPT & any MCP agent. Free on empty runs.

Scrape live job listings from SimplyHired search results. Titles, companies, locations, salaries, job types, descriptions and apply URLs. No login, no anti-bot, pay per job. Use it as an MCP server in Claude, ChatGPT & AI agents.

Detect the CMS, e-commerce platform, JS framework, CDN/host, payments and analytics a website runs, from one HTTP request. 19 technologies, each verified live. No login, no API key.

Extract reviews, ratings, reviewer profiles and owner responses from any TripAdvisor hotel, restaurant or attraction page. Pay per review. Use as an MCP server in Claude & AI agents.

Discover Trustpilot businesses by category or keyword: domain, TrustScore, review count, category and verification status. Feeds domains into the Trustpilot Reviews Scraper. Use as an MCP server in Claude & AI agents.

Scrape Xiaohongshu / RedNote discovery feeds across 11 category channels, with note text, topics, engagement and video URLs, plus creator profiles with followers, bio and niche tags. No login or API key.

Extract Y Combinator startups straight from YC's own directory: company, batch, description, website, industries, and founder names with LinkedIn/Twitter URLs. No login, no browser, pure JSON. Use it as an MCP server in Claude, ChatGPT & AI agents.

Scrape YouTube channel metadata and video list: subscriber count, view count, video titles, view counts and publish dates. No API key needed. Works as MCP tool in Claude.

Download every photo from any Zillow listing at full resolution (up to 1536px), by URL or ZPID. One row per photo. No login, no API key. Works in Claude, ChatGPT & any MCP-compatible AI agent.

Scrape Zomato restaurant listings by city and cuisine: name, locality, address, cuisines, dining and delivery ratings, cost for two, photo. India restaurant data and lead generation at scale. No login, residential proxy. Works in Claude, ChatGPT and any MCP agent.

Monitor App Store and Google Play reviews in one run. Beats Apple's 500-review per-country cap by reading many country storefronts, returning rating, title, text, author, version and date. No login, no API key, pay per review.

Scrape arXiv research papers by keyword, category (cs.AI, cs.LG, quant-ph) or author. Returns titles, abstracts, authors, dates, DOIs & PDF links as clean JSON. No API key. Use it as an MCP server in Claude, ChatGPT & AI agents for research monitoring.

Track where any app ranks for any keyword on BOTH stores, in any country, in one dataset. Rank, rating, installs, developer, price and Apple top chart position, plus a free row naming the tracked apps that did not rank. No API key, no proxy.

Scrape ClinicalTrials.gov trials by sponsor or condition with phase, status & completion date, then auto-flag FDA drug approvals to build pharma pipeline intelligence. No API key. Use it as an MCP server in Claude, ChatGPT & AI agents.

Scrape 150M+ scholarly works from Crossref: DOIs, authors, journals & citation counts by topic, year and type. Clean structured JSON for bibliometrics, literature reviews and RAG. No API key. Use it as an MCP server in Claude, ChatGPT & AI agents.

Scrape Domain.com.au for sale and for rent listings by suburb: price, beds, baths, parking, land size, property type, agent and agency, with photos and coordinates. Australia residential proxy, no login, pay per property.

Product intelligence for AI agents: Amazon products and reviews, AliExpress supplier prices, Shopify catalogs, TikTok Shop, Meta Ad Library competitor ads, and search interest. No result, no charge.

Scrape US federal campaign finance from the official OpenFEC API as clean JSON — search candidates & committees, or pull itemized Schedule A contributions for a committee. No login, no browser needed. Works in Claude, ChatGPT & any MCP agent.

Scrape the US Federal Register for rules, proposed rules, notices & executive orders as clean JSON. Filter by term, agency, type & date. No API key. Works in Claude, ChatGPT & any MCP agent for compliance & RAG.

Search Germany's official Bundesanzeiger, the Federal Gazette where every German company must publish capital changes, shareholder resolutions, insolvency proceedings and financial disclosure notices. Plain HTTP, no login, official primary source. Works in Claude, ChatGPT and any MCP agent.

Look up Legal Entity Identifiers (LEI) and registered company data from GLEIF by name or LEI: legal name, form, jurisdiction, addresses, status, renewal dates, BIC. For KYB, AML, entity resolution. No API key. Works in Claude, ChatGPT and any MCP agent.

Scrape Google Maps reviews: star rating, reviewer name, full text, date, owner response and photo count. Works as MCP tool in Claude, ChatGPT & AI agents. Pay per result, first 10 free.

Scrape Medicare Part D drug spending from CMS: total cost, claims, beneficiaries, unit cost & manufacturer for every brand or generic drug. Structured JSON, no API key. An IQVIA style pharma pricing source for Claude, ChatGPT & any MCP agent.

Scrape NIH RePORTER grants: title, abstract, award $, principal investigator, institution, agency (NCI, NIAID, NIMH), fiscal year. 800K+ grants, no API key. Works in Claude, ChatGPT & any MCP agent.