Web & Data

Detect and redact PII in text: find and mask names, addresses, SSNs, emails, and phone numbers. POST /v1/pii with {text} and get findings and masked output as one JSON object. Deterministic per ruleset version. Pay per request in USDC; no account, no API key.

Load a URL in headless Chromium with JavaScript executed and get the rendered page back for an LLM or RAG pipeline: markdown, text, HTML, title, links and an optional screenshot. POST /v1/render with {url}. Robots.txt is honored and private addresses are refused. JSON in, JSON out, errors included. Pay per request in USDC; no account, no API key.

Extract tables from documents into typed JSON: headers, rows, and cell types. POST /v1/table with {text} and get the parsed tables as one JSON object. Deterministic on clean inputs. Pay per request in USDC; no account, no API key.

Rule-based extraction of named fields from text; not a language model, it returns only what the text states. POST /v1/extract with {text, schema}: schema is a JSON Schema, a list of field names, or {fields: {name: regex}}. Built-in fields include email, phone, date, url, money and company; other fields come from "Label: value" lines. Pay per request in USDC; no account, no API key.

Fetch a web page and return structured data: standard fields (title, description, language, h1, OpenGraph, author, published), headings, JSON-LD and a text excerpt. Optional schema picks named fields or applies regexes to the HTML. POST /v1/url with {url}. JavaScript is not executed; pages are cached for 10 minutes. Pay per request in USDC; no account, no API key.

Search a topic and get the full content of the best pages, in one call. Search, then read the top results, in one call: ranked results from a real web search, and for each of the top pages its main content as markdown, read through a residential IP with a real browser. A page that could not be…

Get a short news briefing on a topic where each point cites its numbered source. Send a topic and receive a sourced news briefing in one call: fresh headlines are collected, then summarised into a s…

Ereignisfeed für Dunkelflaute, Sturm, negative Preise und Rekorde.

Fetch a URL and return its main content as clean Markdown (boilerplate stripped)

Read any public web page as clean text: title, description, canonical URL, the readable body with scripts, styles and navigation stripped, the first 50 links resolved to absolute URLs, and a word count. One URL in, up to 100,000 characters out; redirects are not followed, and a page with no readable text (JavaScript-only) is 422 and not charged. Pay-per-call via x402. An empty body is answered for the published example page (https://example.com/); send {"url":"https://…"} for any other page.

URL -> full page content as clean Markdown, ready for LLM context. Strips nav/ads/scripts, preserves headings/links/lists. Handles redirects, timeouts, size caps, SSRF. The reliable web-reader agents need before feeding a page to a model.

Amazon product search API. Search live Amazon products by keyword and get normalized ASIN, title, current price/range, currency, rating, review count, bought-past-month purchase signal, product URL, image, rank, Amazon Choice/Best Seller flags and delivery text. For shopping agents, Amazon product research, price lookup and ecommerce product discovery.

Newstex MCP Network: one page of metadata-only story search results.

Web search API - live Google (default) or Bing SERP for a query: search engine results returned as ranked organic hits with title, URL, domain and snippet, localised by location and language. A google search api / serp api for agents: search the web, live web search for grounding, RAG and web lookup.

Returns reproducible aggregate statistics for the sanitized Polymathica archive census: 77,053 source rows, unique hashes, domains, file types, readiness and quarantine counts.

Retrieve a bounded passage from the public-domain Berean Standard Bible or World English Bible with exact source labels and provenance.

Find source-linked scientific papers by topic. Returns metadata pointers, authors, dates, licence evidence when supplied by the source, and corpus provenance; it does not sell paper text or infer reuse rights.

Academic literature search over OpenAlex (250M+ works with citation counts) or arXiv: title, authors, year, venue, DOI, abstract

Enumerate a site's URLs from robots.txt + sitemap.xml (sitemap-index aware) — map a domain before crawling it

Parse an RSS/Atom feed into structured items (title, link, published, summary) — or auto-discover the feed from a site URL

Every DefiLlama protocol with current TVL, filtered server-side (the raw index is 8.5MB). Query: chain, category (Lending, Dexes, ...), min_tvl (USD), sort (tvl|change_1d|change_7d), limit (1-100). Each: name, slug, chain, category, tvl_usd, change_1d, change_7d, mcap. Use the slug with /llama/tvl for a live single-number poll.

Deterministic unit conversion reproducing NIST SP 811 exact factors (length, mass, volume, energy, power, pressure, force, area, speed, data, angle, frequency + affine temperature). Every answer signed. Free sample, no payment required: GET /play/unit

Exact structured diff. mode=text -> unified diff + line counts; mode=json -> an RFC 6902 JSON Patch (RFC 6901 pointers) that round-trips a->b; mode=words -> inline word-level opcodes. For large inputs use POST. Every answer signed. Free sample, no payment required: GET /play/diff

Deterministic, rule-based proofreading flags — passive voice, adverbs, wordiness, filler, repeated words, whitespace, a/an, punctuation, sentence length, capitalization. Each flag carries an offset + suggestion. For long text use POST.