AgentTools

Parse a URL into all its components: protocol, hostname, port, path segments, query parameters (as a clean object), hash and credentials. Exact — no guessing by eye. Use this when an agent needs to break any URL into protocol, host, path and params.

Generate cryptographically secure randomness: passwords with charset rules, hex keys of any byte length, and uniform random integers (rejection sampling, no modulo bias). Never use Math.random for secrets. Use this when an agent needs to cSPRNG passwords, hex keys and uniform integers.

Turn a cron expression into plain English, validate it, and compute the exact next execution times. Deterministic — the answer to 'when does this cron actually fire?' without guessing. Use this when an agent needs to explain a cron expression and compute the next runs.

Validate an email address in two layers: strict RFC-style syntax, then a live DNS MX lookup on the domain to confirm the recipient actually runs mail servers. Catches the typos and fake domains that pure regex misses. Use this when an agent needs to syntax + live MX check — can this address receive mail?.

Look up any US telephone area code to find the state or territory it serves, or list every area code in a given state. Covers all 404 NANP codes in use, including overlays. Use this when an agent needs to all 404 NANP area codes → state lookup.

Parse a User-Agent header into structured data: browser (name/version), rendering engine, operating system, and device type/vendor/model. Deterministic — the same string always parses identically. Use this when an agent needs to uA string → browser, engine, OS and device.

Calculate X% of Y, what percent X is of Y, and the percent change between two values — with step-by-step working shown. Use this when an agent needs to percent of a number, ratios and percent change.

Encode text to base64 or decode base64 back to text. Full UTF-8 support including emoji and non-Latin scripts. Use this when an agent needs to uTF-8 safe base64 in both directions.

Add VAT to a net amount or remove VAT from a gross amount. Standard VAT rates for 36 countries are built in, or override with any custom rate. Use this when an agent needs to add or remove VAT at standard rates for 36 countries.

Generate a QR code for any text, URL or crypto address: returns ready-to-embed SVG markup and a data URI, with configurable size and error-correction level. Use this when an agent needs to any text or URL as a QR code (SVG + PNG data URI).

Describe what you need and get back matching x402-paid APIs: our own catalog (54 tools) plus, optionally, the live x402 Bazaar of third-party sellers. The agent's meta-tool — instead of knowing an API exists, ask for the capability. Use this when an agent needs to "I need a tool that does X" → matched paid APIs.

Parse iCalendar (.ics) content — meeting invites, conference calendars, exports from Google/Outlook — into structured event JSON: title, start/end, location, organizer and description. Use this when an agent needs to turn .ics calendar files into clean event JSON.

Check whether a domain name is registered or available, via the official RDAP registry protocol (404 = available). For registered domains it also returns the registrar and creation/expiration dates — useful when an agent needs to name a product or verify how long a business has existed. Use this when an agent needs to is this domain taken? Registry answer, not a landing page.

Reference database of all 250 countries and territories: ISO 3166-1 codes, capitals, regions, population, area, currencies, languages, TLDs and calling codes. Look up a single country or list by region. Use this when an agent needs to 250 countries: codes, capitals, currencies, populations.

Live foreign-exchange reference rates from the European Central Bank (via frankfurter.dev): a full rate table against any base currency, or cross-rate conversion of any amount. Refreshed every business day by the ECB, cached one hour. Use this when an agent needs to live ECB reference rates for 30 currencies.

Live weather from Open-Meteo: current temperature, humidity, wind and conditions plus a 3-day forecast, by city name or coordinates. No API key, cached 30 minutes. Use this when an agent needs to current conditions + 3-day forecast for any city.

List upcoming or full-year public holidays for any covered country via Nager.Date — names, dates and whether they're nationwide. Essential for scheduling agents. Use this when an agent needs to upcoming public holidays for ~110 countries.

Geolocate any IPv4/IPv6 address (or the caller's own IP when omitted) via ipwho.is: country, region, city, coordinates, timezone, ASN/network owner and currency. Cached 24 hours per IP. Use this when an agent needs to where is an IP address? Country, city, ASN, timezone.

Query live DNS records (A, AAAA, MX, TXT, NS, CNAME, SOA) through Cloudflare's DNS-over-HTTPS resolver. Domain validation, email deliverability pre-checks and infrastructure discovery. Use this when an agent needs to real DNS records via Cloudflare DNS-over-HTTPS.

Fetch a URL server-side and extract its title, meta description, Open Graph and Twitter card tags, canonical URL and favicon — the data agents need to preview or classify a link. SSRF-guarded: private networks are blocked, 10s timeout, 1MB cap. Use this when an agent needs to title, description, OG image and favicon of any page.

Split text into retrieval-friendly chunks with a token budget and sentence-aware boundaries. Overlap between consecutive chunks preserves context across splits — the standard preparation step before embedding. Use this when an agent needs to rAG-ready chunks with token budgets and overlap.

Scan unstructured text and extract structured entities: email addresses, URLs, IPv4 addresses, phone numbers and domains. Deduplicated, categorized, machine-ready. Use this when an agent needs to pull emails, URLs, IPs, phones and domains from raw text.

Compare two texts line by line using an LCS diff: exact additions, removals and context — in unified-diff style. Deterministic, unlike asking a model to 'find the differences'. Use this when an agent needs to exact line-level diff with unified-style output.

Fetch an RSS or Atom feed and return normalized JSON items: title, link, publication date (ISO) and summary. Server-side fetching with SSRF guard; handles both RSS 2.0 and Atom dialects. Use this when an agent needs to any feed → clean JSON items, no XML parsing on your side.

Query the Internet Archive's Wayback index for any URL: when it was first archived, the most recent snapshot, how many years it spans, and recent capture dates. Useful for fact-checking page history, finding deleted content and due-diligence. Use this when an agent needs to how the Internet Archive remembers a URL.

Verify a claim about a web page's content: fetches the page (SSRF-guarded) and reports whether the expected text appears, with the surrounding excerpt as evidence. The deterministic way for an agent to confirm 'the site says X' before acting on it. Use this when an agent needs to does this page actually say that? Checked, not guessed.

Probe a GET endpoint several times and report status codes and latency statistics (min/avg/max). The cheap way for an agent to verify an API — for example one found on the x402 Bazaar — responds before spending real money calling it. Use this when an agent needs to status and latency stats — test an API before relying on it.

Live transfer feed of an NFT collection with per-address accumulation analysis: net quantities received vs sent over recent activity, ranking the buyers adding to positions and the wallets exiting. The actionable view behind the raw transfer list. Use this when an agent needs to who is accumulating and who is exiting — right now.

Look up an address's NFT portfolio across collections: each collection held, quantity owned, sorted by size. The enrichment endpoint for agents profiling wallets — pairs with wallet-snapshot for the full picture. Use this when an agent needs to every NFT collection a wallet holds, in one call.

Fetch a PDF (by URL, SSRF-guarded) or accept it as base64 and extract all readable text with page count. Deterministic parsing — no language model, so nothing is invented. Text-based PDFs only; scanned images need OCR (not included). Use this when an agent needs to extract readable text from any PDF — agents can't read PDFs.