# TidyTools > Web data tools for developers and AI agents: website to Markdown for LLM/RAG, screenshots and PDFs, SEO and AI-crawler (GEO) audits, company and contact enrichment, tech stack and domain lookups, email validation, career-site jobs, app store data, transcription, OCR and image tools. 19 tools, each available as an Apify Actor (bulk runs, pay per result, callable by AI agents through Apify's MCP server) and/or a RapidAPI API (one HTTP call per item, free plan with a hard limit). Every tool returns structured JSON, charges only for successful results, and needs no scraping setup. Human-readable catalog: https://tools.yukai.uk/ ## Free, no key: use it right now Any agent or script that can fetch a URL can use these two endpoints. No sign-up, no API key, CORS open; rate limited (about 10 requests per minute per IP), plain HTTP fetch only (no JavaScript rendering, no AI). - **Web page to Markdown:** `GET https://tools.yukai.uk/md/`, for example [https://tools.yukai.uk/md/https://example.com/](https://tools.yukai.uk/md/https://example.com/). Returns `text/markdown` with a YAML header (title, url, status, tokens_estimate, truncated); send `Accept: application/json` for JSON. Up to 100,000 characters. - **Which AI crawlers a site allows:** `GET https://tools.yukai.uk/ai-crawlers/`, for example [https://tools.yukai.uk/ai-crawlers/example.com](https://tools.yukai.uk/ai-crawlers/example.com). Returns JSON: verdict, allowed and blocked bots (GPTBot, ClaudeBot, PerplexityBot and 30+ more), llms.txt and noai signals, and a recommended robots.txt snippet. For JavaScript pages, whole-site crawls, PDFs, RAG chunks, volume or the other tools, use the paid APIs below. ## How an AI agent can call these tools - **MCP (Claude, Cursor, VS Code, n8n AI Agent, any MCP client):** add the remote server `https://mcp.apify.com/?tools=,` with an Apify API token (or OAuth). Example: `https://mcp.apify.com/?tools=tidytools/website-markdown-crawler,tidytools/website-screenshot-pdf-markdown,tidytools/document-to-markdown`. A ready-made configuration is listed in the official MCP Registry as `io.github.tidytools/tidytools-apify-tools` ([repo](https://github.com/tidytools/tidytools-apify-mcp)). - **Apify REST:** `POST https://api.apify.com/v2/acts/tidytools~/run-sync-get-dataset-items?maxTotalChargeUsd=1` with header `Authorization: Bearer $APIFY_TOKEN` and the input as JSON; returns the result rows. `maxTotalChargeUsd` caps the cost. - **RapidAPI:** subscribe to the API's free plan and call it with `X-RapidAPI-Key`; every request is one item. - **OpenAPI specs** of the RapidAPI APIs (import into any client or agent framework): [web-to-markdown](https://tools.yukai.uk/openapi/web-to-markdown.json), [article-summary](https://tools.yukai.uk/openapi/article-summary.json), [website-screenshot](https://tools.yukai.uk/openapi/website-screenshot.json), [link-preview](https://tools.yukai.uk/openapi/link-preview.json), [seo-audit](https://tools.yukai.uk/openapi/seo-audit.json), [ai-crawler-access](https://tools.yukai.uk/openapi/ai-crawler-access.json), [website-contacts](https://tools.yukai.uk/openapi/website-contacts.json), [company-enrichment](https://tools.yukai.uk/openapi/company-enrichment.json), [tech-stack-detection](https://tools.yukai.uk/openapi/tech-stack-detection.json), [domain-whois-dns](https://tools.yukai.uk/openapi/domain-whois-dns.json), [email-validation](https://tools.yukai.uk/openapi/email-validation.json), [company-jobs](https://tools.yukai.uk/openapi/company-jobs.json), [app-store](https://tools.yukai.uk/openapi/app-store.json), [image-ocr](https://tools.yukai.uk/openapi/image-ocr.json), [image-tools](https://tools.yukai.uk/openapi/image-tools.json). - **Copy-paste recipes** (Python, JavaScript, curl, n8n) for every Actor: [https://github.com/tidytools/apify-web-data-recipes](https://github.com/tidytools/apify-web-data-recipes). ## Turn web pages and documents into clean text for AI and apps Crawl a docs site into Markdown for RAG, pull the article out of a news page, render screenshots and PDFs, or turn a page into JSON fields you name. - **Website to Markdown**: Crawl a site or a list of URLs into clean, LLM-ready Markdown with RAG chunks; linked PDFs and Word files included. Apify Actor [tidytools/website-markdown-crawler](https://apify.com/tidytools/website-markdown-crawler) ($1 per 1,000 pages, pay per result); RapidAPI [Web to Markdown for LLMs](https://rapidapi.com/tidytools/api/web-to-markdown-for-llms) (free 300 requests + 20 summaries/month; $9.99/month for 10,000 requests). - **Article extractor & AI summarizer**: News or blog URL to title, authors, dates and clean body; optional TL;DR or bullets in any language. Non-articles are refused before any AI runs. RapidAPI [Article Extractor & AI Summarizer API](https://rapidapi.com/tidytools/api/article-extractor-ai-summarizer-api) (free 200 requests + 30 summaries/month; $12.99/month for 10,000 requests + 1,500 summaries). - **Screenshots, PDFs and Markdown**: Full-page or element screenshots, URL to PDF and Markdown in bulk, with cookie banners and pop-ups hidden. Apify Actor [tidytools/website-screenshot-pdf-markdown](https://apify.com/tidytools/website-screenshot-pdf-markdown) ($1 per 1,000 screenshots, pay per result); RapidAPI [Website Screenshot & PDF](https://rapidapi.com/tidytools/api/website-screenshot-pdf1) (free 100 requests/month; $9.99/month for 3,000 requests). - **Documents to Markdown**: PDF, Word, Excel and CSV to Markdown for LLMs, with optional OCR for scanned PDFs. Apify Actor [tidytools/document-to-markdown](https://apify.com/tidytools/document-to-markdown) ($2 per 1,000 documents, pay per result). - **AI web data extractor**: List the fields you want (or describe them) and get structured JSON from any page, one row per item on list pages. Apify Actor [tidytools/ai-web-data-extractor](https://apify.com/tidytools/ai-web-data-extractor) ($10 per 1,000 pages, pay per result). - **Link preview & URL metadata**: Title, description, Open Graph image, favicon, author, dates and feeds for any URL list. RapidAPI [Link Preview & URL Metadata](https://rapidapi.com/tidytools/api/link-preview-url-metadata1) (free 1,000 requests/month; $4.99/month for 50,000 requests). ## Audit, check and monitor websites Score a page in about two seconds, audit a whole site, see which AI crawlers a site blocks, and get alerted when a page changes. - **SEO audit**: A 0-100 score with a fix for every issue: titles, headings, canonical, robots, sitemap, hreflang, structured data and more. Apify Actor [tidytools/seo-audit-crawler](https://apify.com/tidytools/seo-audit-crawler) ($5 per 1,000 pages, pay per result); RapidAPI [SEO Audit API](https://rapidapi.com/tidytools/api/seo-audit-api15) (free 200 audits/month; $7.99/month for 10,000 audits). - **AI crawler access checker**: Which of GPTBot, ClaudeBot, PerplexityBot and other AI crawlers a site's robots.txt allows, plus Content-Signal and llms.txt. Apify Actor [tidytools/ai-crawler-access-checker](https://apify.com/tidytools/ai-crawler-access-checker) ($2 per 1,000 sites, pay per result); RapidAPI [AI Crawler Access Checker](https://rapidapi.com/tidytools/api/ai-crawler-access-checker1) (free 100 requests/month; $9.99/month for 3,000 requests). - **Website change monitor**: Check pages on a schedule and get email, Slack or webhook alerts with before/after screenshots when content changes. Apify Actor [tidytools/website-change-monitor](https://apify.com/tidytools/website-change-monitor) ($2 per 1,000 checks, pay per result). ## Enrich companies, contacts and domains Start from a domain or a list of websites and get the company profile, the tools it uses, public contact details and the state of its domain. - **Website contact extractor**: Emails, phone numbers and social profiles from company websites, with the page each one was found on. Apify Actor [tidytools/website-contact-extractor](https://apify.com/tidytools/website-contact-extractor) ($2 per 1,000 websites, pay per result); RapidAPI [Website Contact Extractor](https://rapidapi.com/tidytools/api/website-contact-extractor1) (free 50 requests/month; $14.99/month for 10,000 requests). - **Company enrichment**: Domain to company profile: name, description, logo, socials, contacts, tech stack, DNS tools, domain age and open jobs, each with evidence. RapidAPI [Company Enrichment API](https://rapidapi.com/tidytools/api/company-enrichment-api13) (free 100 lookups + 25 AI enrichments/month; $14.99/month for 5,000 lookups + 1,500 AI). - **Tech stack detector**: Frameworks, CMS, hosting, CDN, analytics and email services of a website, with the evidence for each. RapidAPI [Tech Stack Detector](https://rapidapi.com/tidytools/api/tech-stack-detector2) (free 100 requests/month; $9.99/month for 2,500 requests). - **Domain WHOIS, RDAP & DNS lookup**: Registration dates, registrar, availability and DNS records for many domains at once. RapidAPI [Domain WHOIS, RDAP & DNS Lookup](https://rapidapi.com/tidytools/api/domain-whois-rdap-dns-lookup1) (free 500 requests/month; $4.99/month for 30,000 requests). - **Email validation**: Syntax, domain and MX checks, disposable and role-address flags and typo suggestions, without pinging mail servers. RapidAPI [Email Validation API](https://rapidapi.com/tidytools/api/email-validation-api41) (free 500 requests + 10 batch calls/month; $4.99/month for 10,000 requests + 200 batch calls). ## Collect jobs, app store and online store data Read official feeds and public pages into one consistent table: career-site jobs, app reviews and rankings, store catalogues and newsletter posts. - **Career site jobs**: Jobs straight from company career sites on Greenhouse, Lever, Ashby, Workday and more, normalized into one schema. Apify Actor [tidytools/ats-career-site-jobs](https://apify.com/tidytools/ats-career-site-jobs) ($1 per 1,000 jobs, pay per result); RapidAPI [Career Site Jobs API](https://rapidapi.com/tidytools/api/career-site-jobs-api1) (free 100 requests/month; $14.99/month for 10,000 requests). - **App Store reviews & app details**: Ratings, reviews and app details from the Apple App Store (and Google Play app details on the API). RapidAPI [App Store Reviews & Top Charts](https://rapidapi.com/tidytools/api/app-store-reviews-top-charts1) (free 100 requests/month; $9.99/month for 5,000 requests). ## Transcribe audio and read or edit images Speech to text with timestamps and SRT subtitles, text from receipts and screenshots, alt text for accessibility, and bulk image clean-up. - **Audio & video transcriber**: Speech to text with timestamps, speaker labels, summaries and translated SRT subtitles; podcasts and files. Apify Actor [tidytools/audio-transcriber](https://apify.com/tidytools/audio-transcriber) ($0.006 per audio minute, pay per result). - **Image to text (OCR)**: Text from receipts, documents, screenshots and photos in many languages. RapidAPI [Image OCR API](https://rapidapi.com/tidytools/api/image-ocr-api) (free 50 requests/month; $9.99/month for 2,000 requests). - **Background removal & image tools**: Remove backgrounds (transparent or any color, crop to subject), resize, convert to WebP/AVIF and compress. RapidAPI [Background Removal & Image Tools API](https://rapidapi.com/tidytools/api/background-removal-image-tools-api) (free 50 requests/month; $9.99/month for 3,000 requests). ## Optional - [AI Crawler Index](https://tools.yukai.uk/ai-crawler-index): free daily dataset of which popular websites block GPTBot, ClaudeBot, PerplexityBot and other AI crawlers. - [All TidyTools Actors on Apify](https://apify.com/tidytools) and [all TidyTools APIs on RapidAPI](https://rapidapi.com/user/tidytools).