Agent Tools UK
Pay-per-use agent tools: screenshots, web to Markdown, PDF tables, OCR, UK company checks
| Endpoint | https://agent-tools-production-e6aa.up.railway.app/mcp (streamable-http) |
|---|---|
| Registry version | 1.2.0 |
| Now | 18 tools · grade A (94) · pin ts_6eecebd7aef2b323c6bd16ce5a41bfed · protocol 2025-06-18 |
| First / last listed | 2026-11-14 01:27 UTC / 2026-11-14 01:27 UTC |
| Grade over time | 2026-11-14: A (94), 18 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: screenshot_webpage webpage_to_markdown pdf_tables_to_json ocr_read_text document_to_json ocr_batch convert_file html_to_pdf transcribe_audio uk_postcode_lookup uk_company_check website_status_check seo_page_audit broken_link_check page_change_check domain_dns_lookup sitemap_reader extract_structured_data
screenshot_webpage | Render any public web page in a real Chrome browser and return a PNG screenshot. Use when you need to see how a page looks, check a layout, capture visual evidence, or read content that only appears after JavaScript runs. Options: width 320-2560 (default 1280), full=true for the whole page. Errors: 400 bad or private URL, 504 page took over 30s. Price: $0.01 USDC per call (x402). params: url*, width, full |
webpage_to_markdown | Fetch a public web page and return just the main article as clean Markdown, with title, byline and excerpt. Menus, ads and footers are removed. Use when you need to read, summarise or quote a web page cheaply without parsing HTML yourself. Returns JSON {title, byline, siteName, excerpt, markdown}. Errors: 400 bad or private URL, 422 no readable article, 502 site returned an error. Price: $0.003 US params: url* |
pdf_tables_to_json | Extract every table from a PDF and return it as rows of cells in JSON, with the page number of each table. Use when you need numbers from financial statements, invoices, price lists or reports that are locked in a PDF. Send {url} or {base64}. Max 20 MB, first 50 pages. Returns {pages, tables:[{page, rows}], truncated}. Errors: 400 not a PDF, 413 too large. Price: $0.01 USDC per call (x402). params: url, base64 |
ocr_read_text | Read the text from a photo, screenshot, scan or scanned PDF (OCR). If the PDF already has real text, that is returned instead (faster and exact). Use when text is only available as an image: receipts, letters, forms, signs. Send {url} or {base64}, optional lang (default eng, e.g. eng+fra). Max 20 MB, 20 pages. Returns {text, method, pages}. Errors: 400 bad input, 413 too large. Price: $0.01 USDC p params: url, base64, lang |
document_to_json | Read a whole document in one call: all the text (OCR for scans and photos, exact text for digital PDFs) plus every table as rows of cells. Use when processing invoices, receipts, bank statements, contracts or reports and you need both the wording and the numbers. Send {url} or {base64}, optional lang. PDF or image, max 20 MB, 20 pages of text, 50 of tables. Returns {type, pages, method, text, tabl params: url, base64, lang |
ocr_batch | Read the text from up to 10 images, scans or PDFs in one paid call, cheaper than one call per file. Use for a stack of receipts, pages of a scanned letter, photos of forms or a folder of screenshots. Send {files:[{url} or {base64}], lang}. Max 30 pages across the batch, 20 MB per file. Each file gets its own result or error. Returns {files, pages, results:[{index, text, method, pages}]}. Errors: 4 params: files*, lang |
convert_file | Convert office documents and images between formats. Documents (docx, doc, xlsx, xls, pptx, ppt, odt, rtf, html, txt, csv) to pdf, docx, odt, txt, xlsx or csv; images between png, jpg, webp and gif. Use when a user or system needs a file in a different format. Send {url} or {base64}, plus filename (with extension) and to. Returns the converted file. Errors: 400 unsupported pair, 422 conversion fai params: url, base64, filename*, to* |
html_to_pdf | Turn HTML you write (an invoice, report, letter or certificate) or a public web page into a print-quality PDF, rendered by Chrome with backgrounds and CSS. Use when you need to hand a person a polished, printable document. Send {html} or {url}; optional format (A4, Letter, A3, A5, Legal) and landscape. Returns the PDF. Errors: 400 missing input or private URL, 413 HTML over 2 MB. Price: $0.01 USDC params: html, url, format, landscape |
transcribe_audio | Speech to text: turn a voice note, phone call, meeting recording, podcast clip or video (mp3, m4a, wav, ogg, mp4, webm, up to 15 minutes) into text with timestamps, using Whisper. Language is detected automatically. Use when you need the words, a summary or quotes from audio or video. Send {url} or {base64}, optional language (2-letter code). Returns {language, duration, text, segments}. Errors: 4 params: url, base64, language |
uk_postcode_lookup | Look up any UK postcode and get latitude/longitude, local council, county, ward, parish, parliamentary constituency, region and country, from official ONS data. Use when you need to place a UK address on a map, work out which council or MP covers it, or check a postcode is real. Spaces optional. Errors: 400 invalid format, 404 postcode not found. Price: $0.001 USDC per call (x402). params: postcode* |
uk_company_check | Verify a UK business on the official Companies House register by company NAME or NUMBER: legal name, status (active, dissolved, liquidation), type, incorporation date, registered address, SIC codes, accounts overdue, charges, insolvency history and current directors. Use for KYB, supplier or customer checks, due diligence, or confirming a UK business is real and active. Name searches also return o params: number* |
website_status_check | Check whether a website is up right now: HTTP status, response time in ms, full redirect chain, and the SSL certificate's validity, issuer and days until expiry. Use when monitoring a site, diagnosing a broken link, or warning that a certificate is about to expire. A site that is down still returns 200 with up:false and the error. Errors: 400 bad or private URL. Price: $0.002 USDC per call (x402). params: url* |
seo_page_audit | Audit a web page's SEO and sharing tags in one call: title and meta description (with lengths), canonical, robots/noindex, lang, viewport, H1/H2 headings, word count, image alt text, internal/external links, Open Graph and Twitter cards, hreflang and schema.org types, plus a plain-English list of issues and a score. Use when reviewing or fixing a page for search or social previews. Errors: 400 bad params: url* |
broken_link_check | Find broken links on a web page: collects every link on the page and checks each one (up to 200, in parallel), returning the broken ones with their status code or error and link text. Links that answer 401/403/429 (often bot protection) are listed separately. Use when maintaining a site, auditing content or before publishing. Optional limit (default 100, max 200). Returns {linksFound, checked, ok, params: url*, limit |
page_change_check | Check whether a web page has changed since you last looked. Returns the page's main text and a fingerprint (hash); send back previous_hash to get changed true/false, or previous_text to also get the lines added and removed. Optional CSS selector to watch just one part (a price, a stock status, a notice). Use for monitoring prices, policies, job boards, competitors or announcements. Send {url, prev params: url*, previous_hash, previous_text, selector |
domain_dns_lookup | Look up a domain in one call: DNS records (A, AAAA, MX, NS, TXT, CAA, SOA), email security (SPF, DMARC and its policy) and registration from RDAP (registrar, created, expiry date, days to expiry, status). Plain-English notes flag missing SPF/DMARC or a domain about to expire. Use for domain due diligence, email deliverability checks, phishing triage or checking a site's setup. Send domain (example params: domain* |
sitemap_reader | List a website's pages from its sitemap: reads robots.txt (sitemaps, allow/disallow rules for all crawlers, crawl-delay), then the sitemap(s), following sitemap indexes and .gz files, and returns page URLs with last-modified dates. Use before crawling or summarising a site, to find new or updated pages, or to check what crawlers may access. Send a site URL or a sitemap URL; optional limit (default params: url*, limit |
extract_structured_data | Pull the machine-readable facts from a web page: schema.org JSON-LD and microdata, products with prices, currency, availability and ratings, the organisation's name, logo and address, and contact details (emails, phone numbers, social profiles), plus Open Graph tags. Use for price checks, lead research, building a company profile or reading product pages without parsing HTML. Returns {types, organ params: url* |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.