Opens each URL in a cloud browser and returns one tab per URL, in input order, with the title, content type, extracted text, the accessibility tree and a link map. Results over the inline size limit return a preview per tab plus a download reference. Each call is one request.

Give it npm or PyPI package names. For each it reads the registry metadata and latest version (and npm download counts) and queries OSV.dev for known security advisories, then composes a risk brief: known vulnerabilities, deprecation, staleness and a signal. Keyless, agent-callable. One search per call (result caps in the input schema); failed lookups are not charged.

Token safety / honeypot / rug-pull check for SOLANA (incl. pump.fun), Ethereum, BSC or Base: Solana mint & freeze authority, Token-2022 traps, top-holder and insider concentration, LP locked, liquidity, buys vs sells; EVM sell simulation and taxes. One 0-100 safety score + verdict. Signals, not advice.

Solana wallet profile: account type, SOL balance, recent activity, failed-transaction share and velocity from the RPC, plus the wallet's record on new tokens in our trade data (tokens entered, early entries, hit rate, rugs, realized USD) and a label: smart / sniper-bot / active / new / unused.

Translate text between French (including Quebec French) and English, with optional tone. Pay-per-call over x402 in USDC on Base; payment challenge answered in ~25 ms, 7-day average processing ~1.5 s across Tolca services.

Fetch any URL (web scraping / URL fetch) and get the raw content: HTML/JSON/text as text, images and PDFs as base64 (for multimodal LLM input), or markdown. Final URL after redirects, status, content type, size. Fetched from Cloudflare's edge (fallback for sites that block it), up to 5 MB. Error statuses are not charged.

Search the US National Archives (NARA) catalog by keyword or record ID and get every digitized file: direct download URL, file type, title, date and record hierarchy. Use it to find and fetch historical government documents, photos and records. Keyless, public domain. Up to 3 items per call; failed lookups are not charged.

Email preflight 11–50 addresses for $0.005 per batch. Ordered syntax/DNS/MX/disposable evidence and explicit unknowns. Addresses processed, not intentionally logged in routine telemetry. No mailbox, deliverability or consent guarantee. Bazaar response example shows the first result only; actual response includes all items.

Given a website domain, reports which AI crawlers may fetch its home page under its robots.txt (RFC 9309): GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended, Applebot-Extended, CCBot and more, each allowed or blocked, plus Googlebot, listed sitemaps, whether /llms.txt is published and page-level noindex/nosnippet, with fixes. Static check, no browser. Not charged if robots.txt cannot be read (no response, or a bot block).

Weather, air quality (AQI, PM2.5) and nearby earthquakes for any place on Earth in one call, plus a clear/caution/hazard verdict with reasons. Use it to check conditions or hazards at a location; many locations per run. Keyless (Open-Meteo + USGS); webhook alerts. Up to 3 items per call; failed lookups are not charged.

Wikipedia & Wikidata API: give any company, person, place or thing and get one structured record: summary, Wikidata ID, key facts (country, founded, HQ, CEO, website, industry...), image and 30-day pageviews. Use it for LLM grounding and entity enrichment. Keyless, bulk. Up to 3 items per call; failed lookups are not charged.

Country economic data for any country (ISO code): World Bank GDP, GDP per capita, population, growth, inflation and unemployment, plus the live USD exchange rate and upcoming public holidays. One structured record per country for market research or agents. Keyless. Up to 3 items per call; failed lookups are not charged.

Scrape website page to Markdown. Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; optional section ID. Default 20,000 output characters, max 100,000; input 2 MiB. No JavaScript rendering (see /extract/rendered), logins or paywalls. Empty pages, bad sections, browser challenges and errors are not charged. Use to read docs or articles.

Is this package safe to install? One call, one verdict: safe / caution / avoid, with a score, concrete reasons (known vulnerabilities from OSV, deprecation, abandonment, adoption, install scripts, typosquat signals) and a one-line recommendation. Input: name, ecosystem (npm | PyPI), optional version.

Summarize text (up to 40k chars) into a faithful, tight summary, with optional max_words and target language. Pay-per-call over x402 in USDC on Base; payment challenge answered in ~10 ms, 7-day average processing ~1.5 s across Tolca services.

Give it domains. For each it queries keyless RDAP (the modern WHOIS) and reports the registrar, creation and expiry dates, days until the domain expires, registry status/locks, nameservers and DNSSEC - with a signal (active / expiring-soon / expired / at-risk). Schedule + webhook for expiry alerts. Up to 3 items per call; failed lookups are not charged.

Give it hosts or HTTPS URLs. For each it does a passive TLS handshake and reports the certificate: validity, days until expiry, issuer, subject, SANs and TLS version - with a signal (valid / expiring-soon / expired / invalid / unreachable). Schedule + webhook for expiry alerts. Keyless. One search per call (result caps in the input schema); failed lookups are not charged.

Domain lookup in one call: DNS A/AAAA, MX mail servers, NS, SPF/TXT, homepage title and tech hints, social profiles and public contact emails for any domain. Use it for lead enrichment, KYB checks and email deliverability. Keyless, bulk. Up to 3 items per call; failed lookups are not charged.

Give it domains. For each it resolves the core DNS records over keyless DoH and runs best-practice checks - does it resolve, enough diverse nameservers, DNSSEC, CAA, IPv6, SPF/DMARC present - into a health signal with findings. Read-only public DNS, agent-callable. One search per call (result caps in the input schema); failed lookups are not charged.

From a company domain or work email, names its email provider (Microsoft 365, Google Workspace), security gateway, MS tenant, DMARC, sending tools, SSO and the SaaS it verified (Atlassian, Okta, Zoom, OpenAI...) - all from public DNS. Up to 3 items per call; failed lookups are not charged.