Search & web

Amazon product search API - search Amazon products / find products on Amazon by keyword (US). Live Amazon product data: ranked listings with ASIN, title, product URL, image, price range, currency, star rating, review count and Amazon's Choice / Best Seller flags. No matches returns empty results.

Fetch any public URL, render client-side JS, strip nav/ads, return clean LLM-ready Markdown.

+1 more from gate402

URL-to-Markdown web extraction and context compression for AI agents. Fetch a public web page and return clean, task-relevant, citation-verifiable LLM context with exact excerpts, locators, hashes, and estimated tokens saved. Use before an agent summarizes, answers questions from, or cites a long or noisy URL. Deterministic and model-free. Public HTML only; no PDFs, logins, or JavaScript-only pages.

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.

Extract clean readable text and metadata from a public webpage and return structured JSON for AI agents.

DNS lookup over Cloudflare DoH: query A, AAAA, CNAME, MX, NS, TXT, SOA, SRV, CAA or PTR records for any domain and get structured JSON answers with TTLs. Useful for domain research, email validation and infrastructure checks.

+2 more from AgentReader

Search Twitter/X for user accounts matching a keyword or phrase. Returns up to 20 matching user profiles per page with pagination support. Useful for discovering users by topic, name, or keyword. Query params: query (string, required) - search keyword or phrase; next_token (string, optional) - pagination cursor from previous response, e.g. GET /users/search?query=bitcoin. Returns X v2 API-compatible JSON.

Use this to search market titles plus the latest Q summary for a shortlist of recent, open contracts. Returns 10 results by default, at most 20. Use direct topic keywords. Useful alternate angles may use focused searches within a 10-second discovery budget. On a timeout, return candidates already found instead of retrying. Use explicit as_of only for historical questions. Search does not expand graph relationships or run embedding search.

+2 more from quotient-api-gateway.onrender.com

Scrape any public web page and get clean structured JSON (title, text, meta). Pay per call with USDC on Base.

Read any web page as clean text: give a URL, get the visible text rendered in a real browser, with the title and final URL. For scraping, RAG and research.

Call when you need the readable content of a public web page: returns clean markdown (title, headings, lists, links; scripts and navigation removed), up to 100k characters. Pages that fail (404, blocked, timeout) are not charged.

Pre-execution decision for a metered search or browse tool call. Evaluates the proposal; does not execute the external tool.

Search Mint & Marquee for gifts and collectibles: products that match what the person wants, under their budget, with price, photo, a short description and a link to buy. Custom 3D printed collectibles and gifts: figurines, statues, keychains, bag tags and branded merch. Soccer, anime, crypto, hypebeast and ancient-art collections.

Use to fetch page metadata from a URL: title, description, Open Graph, favicon, HTTP status, and content type. Optional main-content text. One URL or items[]. Not article text (Web Content Cleaner) and not a link list (Link Extractor). If error is worker_chunk_failed, retry those items; the URL was not fetched. The HTTP body has correlation_id and data. The item array is data.results.

Use to list links on a page as structured rows: url, title, desc, rel, nofollow, internal/external, and kind. Not cleaned article body. An empty page returns item error no_links. After filter and dedupe, all unique links are returned; truncated_links is always false.

Use to extract readable text from a homepage or hub URL. Not a single-article extract (Web Content Cleaner) and not a structured link list (Link Extractor). If the requested extract has no main content, the other profile is tried once in the same request.

Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tried once in the same request. The HTTP body has correlation_id and data. The item array is data.results.

Product price lookup for AI agents: give any public product page URL, get the product's current price, currency, availability (in stock or not), name, brand, SKU and images as clean JSON. The page is rendered in a real browser, so JavaScript stores work, and the store's own schema.org product data is read first. For price checks, price monitoring and comparing stores before you buy.

Search your stored memories by meaning, like mem0's search: embeds the query and returns the closest memories with a relevance score from 0 to 1. Only memories stored under the same memory_key (your secret string; required) are searched. filters must name at least one of user_id, agent_id, app_id, run_id. Returns {results:[{id, memory, score, metadata, ...}]}.

Text to JSON: Extract Data Without Guessing — Extracts data from text into JSON that matches the shape you give (a JSON Schema, an example object or a list of fields), without guessing. Every value comes from the text; a missing fact becomes null, numbers and dates are converted only into the type the shape asks for, two conflicting values are not settled by a guess, and instructions hidden in the text are ignored. Use when asked to extract structured data, turn text into JSON, parse an invoice…

Classify the search intent behind keywords: for each keyword, the dominant intent (informational, navigational, commercial or transactional) with a probability, plus any secondary intents. For mapping a keyword list to funnel stage and content type. Up to 1000 keywords per call.

Fetch a reviewed public page and return its links with resolved absolute URLs and anchor text, the canonical URL, the declared meta robots directive, and how many links leave the host. Relative hrefs are resolved against the page, so a caller never has to guess a base.

Google Shopping product search API - search Google Shopping by keyword (US) and get ranked product offers across sellers. Live Google Shopping data: title, product URL, image, seller, price, currency, star rating, review count, Google product id and delivery info. Compare product prices across merchants. No matches returns empty results.

One-call research brief: live web search synthesized into a cited bullet report — every claim tied to a source URL from the results. Same shape as /api/v1/search (query, optional k/freshness/domains) with a written summary on top. $0.05 per call over x402 — no account, no API key.

+2 more from ioswarm.io

3ilm vulnerability pattern search — 1032 exact-reconciled findings from 10 Sherlock contests

Extracts OG tags, canonical URL, title, and meta description from any web page. Useful for link previews, SEO audits, and content enrichment.

+4 more from shelf.thirdmade.net

Returns matching workflows from 819 agent automation prompts with slug, title, description, and complexity — use it to find a ready-made automation instead of building one from scratch. Search by keyword to locate a Slack-to-Notion sync, an email-to-CRM pipeline, a dev-tool integration, or any pre-built workflow an agent can run directly, ranked by relevance with pagination via limit and offset.

Return the Schema.org structured data already published on a public web page. Navigation-only results are marked low information so agents can choose Full extraction. $0.005 USDC per successful request on Base. Call /check before paying. Payment authorization settles only after a successful response.

+2 more from jsonrecon.com

Find a domain's organic search competitors: rival domains ranking for the same Google keywords, each with the number of common keywords, average position, total ranked keywords and estimated organic traffic. For competitive SEO research. Empty results if none.

Extract keywords: Verb-path alias of POST /v1/cheap-errand ($0.01 USDC). Same handler + payment terms; path defaults task=extract_keywords when body.task omitted. Cheap agent glue for buyer-supplied text. Base via x402. No API key.

+2 more from x402.hydratrader.ai