The Mine Works

Search the full text of every SEC EDGAR filing since 2001 across all companies. Find any phrase or risk factor in 10-K, 10-Q, 8-K, S-1 filings. Filter by form and date. Clean JSON, no API key. Works in Claude, ChatGPT and any MCP agent.

Scrape the full product catalogue of any Shopify store — title, vendor, type, tags, variants, price range, SKUs, stock and images. Uses each store's public products feed: no login, no API key, no browser. Competitor and dropshipping research. Use it as an MCP server in Claude, ChatGPT & AI agents.

Scrape any Substack newsletter archive: title, subtitle, full post text, author, publish date, reactions, comment count and whether the post is behind the paywall. No login, no API key, pay per post.

Scrape every public post from any Threads profile by username. Text, timestamps, likes, replies, reposts, media URLs and permalinks. Optional monitor mode returns only new posts on a schedule. No login, no API key. Works in Claude, ChatGPT and any MCP compatible AI agent.

Scrape Alibaba.com wholesale search by keyword: price range, MOQ, supplier name, country, ratings and trust signals. Currency pinned to USD. No login, no API key.

Scrape current rental vacancies from any AppFolio property manager portal: rent, beds, baths, square feet, address with map coordinates, availability, pet policy, photo and apply link. Add the manager's website to get their office phone. Filters included. No login. Pay per vacancy.

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.

Full backlink outreach pipeline: discovers real guest-post & resource-link prospects for your topic, extracts a verified contact from each site, and drafts a personalized outreach email with AI. Billed only for outreach-ready leads. Never sends email.

Building permits from 12 US and Canadian city open data portals in ONE schema: contractor name, phone, licence, owner, valuation and a derived project class (solar, roofing, HVAC, new build). Plus a contractor rollup. No API key, no proxy.

Scrape current rental vacancies from any Buildium (managebuilding.com) property manager: rent, deposit, beds, baths, square feet, address, availability, pets, amenities, photos, apply link and the office phone and email. One request per manager. Filters included. No login. Pay per vacancy.

Scrape ClinicalTrials.gov in bulk: filter 575k+ trials by phase, status, condition, drug or country. Clean structured JSON with eligibility criteria, sponsors & enrollment. No API key. Use it as an MCP server in Claude, ChatGPT & AI agents.

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 the official UK Companies House register: company number, status, type, incorporation date, registered office address, SIC codes and full officer roster. Search by name or look up company numbers directly. Bring your own FREE Companies House API key. Works in Claude, ChatGPT & any MCP agent.

Official-registry company diligence for AI agents: SEC EDGAR, GLEIF LEI, EU VAT, court records, federal awards, reputation. No result, no charge.

Resolve a company domain to its LinkedIn company page URL. Checks the company's own homepage for its LinkedIn link first, falls back to a search only when that link isn't there. No login, no API key.

Scrape Douyin (Chinese TikTok) trending topics with hotness scores, and every video under any hashtag: description, duration, video and cover URLs. No login, no API key.

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.

Scrape github.com/trending by language and time window (daily/weekly/monthly). Rank, stars, forks, stars gained, description, language. There is no official API for GitHub Trending. This is the only way to get it programmatically.

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 Play Store search results: app name, package id, developer, rating, icon and store URL. Any country and language. No login, no API key.

Scrape Gouden Gids (goudengids.nl) by trade and town: business name, phone, address, coordinates, website, opening hours and KvK number. Turn on emails to find each business's address from the directory or its own website, charged only when found. Pay per business.

One row per US provider joined across three federal sources: NPPES identity, licence, address and phone, plus CMS Open Payments industry money received and Medicare Part D prescribing volume. 8M+ NPIs. No API key, no proxy.