Search & web

Full agent-readiness report for a website or API: everything in the readiness audit plus a quality review of the agent card, OpenAPI document, llms.txt, MCP server (connects, tools, descriptions) and pay-per-call manifest (does a listed endpoint really answer 402), CORS for in-browser agents, and an AI-written prioritised fix plan.

+2 more from api.manylives.me

Class action lawsuit search via CourtListener - case name, court, date and citation

+1 more from Saylor Innovations Class Action

robots.txt rules for a user-agent - allow and disallow rules, crawl delay and sitemap URLs

+1 more from Saylor Agent Tools

Search 75,000+ public-domain books on Project Gutenberg by title or author

Search the Protein Data Bank for 3D structures by free text - title, method, resolution and release date

+2 more from Saylor Innovations Bioinformatic

Keyword and key phrase extraction from text with relevance scores (RAKE)

Traffic Reality Check: Real Readers vs Bots — Reads the numbers from Cloudflare Web Analytics and zone analytics (GraphQL or the dashboard) and says how many of them are real readers or real server errors, answered as JSON with the computed figures and a short reason. Knows what pollutes the table - the owner's own headless-browser checks, link-preview fetches from the social network that show up as referrals, the site's own Worker and its cache calls counted as visitors or as 5xx errors, the r…

Juniper x402 API Buyer Pack: Search, Scraping & USDC Budget Guard. Discover x402 APIs for web search, scraping and finance data. Includes 28 live quote-checked endpoints across 6 providers, First approved purchase: 0.01 USDC total where maker terms permit; later 1 USDC plus tax. Stored ZIP download; commercial use, no redistribution. Verified by Speedbot for this version. Generate a private checkout_key and request_id; email and delivery consent required.

Clinical trial lookup against the full ClinicalTrials.gov registry: exact lookup by NCT number, or search by condition, intervention, or lead sponsor. Returns compact trial summaries (status, phases, conditions, interventions, enrollment, sponsor, dates, results availability). U.S. National Library of Medicine / NIH registry data.

Google Trends related queries for one keyword: the top related searches (0-100) and the rising ones (% growth), for a country or worldwide, past 7 days to 5 years, in one $0.03 GET. Use when you need query expansion, content ideas or emerging searches around a keyword. A live call takes up to about 30 s. Bad input is free; upstream errors are not charged.

Google Trends interest over time for one keyword: a dated 0-100 series for a country or worldwide, past 7 days to 5 years, in one $0.045 GET. Use when you need search-interest trends, seasonality or demand direction for a keyword. Daily points for short windows, weekly for 12 months. A live call takes up to about 30 s. Bad input is free; upstream errors are not charged.

Keyword ideas for a seed keyword, each with Google search volume, CPC, competition, keyword difficulty and search intent; up to 100 ideas in one $0.04 call (DataForSEO Labs). Use when you need related keywords to target. volume = avg monthly searches, cpc in USD, competition 0-1, difficulty 0-100. No ideas returns empty results (still charged). Bad input is free; upstream errors are not charged.

Reader Pro: fetch a public web page and return structured data, no LLM: OpenGraph/meta tags, parsed JSON-LD (schema.org), HTML tables as row objects, deduped internal/external links, emails/phones/social profiles, heading outline, images with alt text, plus optional CSS-selector fields.

+1 more from softbot-reader-mainnet.softbot.workers.dev

Search parking lots worldwide by name, place, setting, facility, amenity and status, or find the nearest to a point: a page of up to 100 lots with live free spaces, hourly prices in USD and distances, and per-country totals; sorted and nearby results come in one page

Fetch a public web page by URL (or take your HTML) and return Markdown plus headings. No JavaScript rendering. Result carries a signed receipt.

Finds the contradictions on a caller-supplied product page that make a buying agent abort: offer price in JSON-LD or Microdata against the prices visible in the text, structured availability against sold-out and add-to-cart signals, JSON-LD against Microdata, variants that cannot be told apart, shipping cost and return period as data or only as prose. Returns a verdict with every contradiction and gap explained. Machine extractability, not price law; no checkout, no outbound request.

Fetch multiple computed series in one call (the sum of each series price)

Call before onboarding, screening or paying a counterparty: full-text search of SEC EDGAR filings for an enforcement/regulatory phrase; returns matching filings (company, CIK, form, filed/period, state, SIC, accession + official sec.gov deep-link). Phrase search: quote your term, filter by form/date.

Call before onboarding, screening or paying a counterparty: full-text search of SEC EDGAR filings for an enforcement/regulatory phrase; returns matching filings (company, CIK, form, filed/period, state, SIC, accession + official sec.gov deep-link). Phrase search: quote your term, filter by form/date.

pump.fun's coin search: matches on name, symbol, description or mint, ranked by USD market cap. Returns full coin records (mint, metadata, market cap, creator, bonding-curve state). Use to resolve a ticker or name to a mint.

Search US commercial real-estate listings on Crexi by city or keyword, property type and price band, returning asking price, square footage, address, county, coordinates and brokerage. Paywalled '****' placeholders are dropped, never passed through as values.

+5 more from Scrapebench API

Full text of one section of the FDA Investigations Operations Manual (IOM). Get the id from GET /search?q=<keywords> or GET /chapter/:id. Use this when you need the complete, verbatim text of a specific IOM section for inspection-readiness or regulatory research, not a summary.

VALUNARIA BUS-WEB web.extract.v1

Pull named fields out of unstructured text as strict JSON. You name the fields, you get an object back.

Skuuy Read — URL to clean Markdown (100 reads/day free)

+1 more from Skuuy Read

Read any public web page as clean readable Markdown for RAG and LLM pipelines — main article text with nav/ads stripped, plus title. ?url=https://example.com&max_chars=20000

+5 more from Pyfile x402 API

Extract article text and metadata from a URL

Search the public universe of MCP servers. This data comes from the Official MCP Registry.

Real-time booking for Korean beauty & wellness shops — search availability, get a booking link.