Web Search Research x402 offerings

Web content extraction and search. Get clean markdown from any URL or search results.

Web content extraction and search. Get clean markdown from any URL or search results.

Search the web and return relevant results for a query.

Website crawler: read a whole website or one section of it (for example every page under /docs) as clean Markdown: starts at a URL, follows same-site links breadth-first and returns up to 20 pages with title and description. Use for documentation, product catalogs or company sites. For one page use web-scrape, for a known list of URLs web-read-batch (up to 5) or web-scrape-batch (up to 20). Charged only if at least one page was read.

Everything a reviewed public page declares, in one call and one fetch: title, meta and Open Graph, canonical, robots directive, JSON-LD with its schema.org types, resolved links with an external count, tables, content fingerprints, and readable Markdown. Replaces six separate extraction calls, and adds the cross-checks none of them can make alone — a canonical that disagrees with the URL you asked for, a page declaring noindex, missing structured data.

Website screenshot: screenshot any URL as a PNG in a real browser. Returns image_base64 (base64 PNG; decode to get raw bytes). Full JS rendering via Playwright, works on SPAs and dynamic content. Params: url (required), width px (default 1280), height px (default 800), full_page boolean, wait_ms.

Instant website SEO audit. On-page SEO, performance, and accessibility snapshot for any URL — title, meta tags, headings, links, image alt, load time, and an issues list with score.

WhiteMagic hosted recall — agent memory for cross-session continuity: read-only hybrid search (BM25 + vector + associative) over a curated public corpus. Call when an agent needs durable context from prior sessions or the public knowledge store. Keyless discovery (initialize/tools/list) is free; free evaluation keys and a daily no-key trial are available. One paid tool call per payment.

Use to find the right Wikipedia article before reading it: full-text search over one Wikipedia language edition, returning up to 20 results with title, plain-text snippet, page URL, word count and last edit time, ranked by relevance. Results are titles and snippets only; use /v1/summary for content.

Use when you need a short, sourced explanation of a topic, place, organization, product or concept: returns the Wikipedia article's lead section as plain text plus title, short description, thumbnail and original image, page URL, Wikidata ID and last-modified time, in any Wikipedia language (redirects followed). Every response carries the CC BY-SA 4.0 license, credit line and source link required for reuse. Articles about individual people are not served (non-personal data only).

Use when you need a short, sourced explanation of a topic, place, organization, product or concept: returns the Wikipedia article's lead section as plain text plus title, short description, thumbnail and original image, page URL, Wikidata ID and last-modified time, in any Wikipedia language (redirects followed). Every response carries the CC BY-SA 4.0 license, credit line and source link required for reuse. Articles about individual people are not served (non-personal data only).

Use to find the right Wikipedia article before reading it: full-text search over one Wikipedia language edition, returning up to 20 results with title, plain-text snippet, page URL, word count and last edit time, ranked by relevance. Results are titles and snippets only; use /v1/summary for content.

Search Wikidata for entities matching a text query, returning candidate Q-ids with labels and descriptions.

Fetch a Wikidata entity by Q-id: label, description, aliases and its claims (property → values).

Summary of a Wikipedia article in any language: title, short description, lead paragraph, image, coordinates, link and Wikidata id. If the title is not exact it returns the closest article, flagged as approximate, with alternatives.

Wikipedia article summary — plain-text and HTML extract, short description, thumbnail and Wikidata id for any title, in a clean normalized envelope with CC-BY-SA attribution.

Keyless fact-grounding: search Wikipedia for any topic and get the matching article titles with extract snippets and canonical URLs — the cheap knowledge read agents make to ground answers and reduce hallucination. Free upstream (Wikimedia API).

Quick factual lookup: a plain-language summary (abstract) plus up to 5 relevant links from Wikipedia. Best for people, places, concepts, history and science. Returns links, not page content: to get the content of the top results in the same call, use search-read. Not for breaking news: use news-search. Params: query (required).

Web search returning URLs, titles, and descriptions

Find articles written by or mentioning a person

Read a web page and extract content as markdown with screenshot

Service: Wolfram Alpha (https://wolframalpha.x402.paysponge.com/v2/query)

Service: Wolfram Alpha (https://wolframalpha.x402.paysponge.com/v1/result)

Service: Wolfram Alpha (https://wolframalpha.x402.paysponge.com/v1/simple)