Use before citing a paper, especially one an LLM produced: checks a DOI, arXiv id or title against Crossref, OpenAlex and arXiv. VERIFIED, RETRACTED, YEAR_DIFFERS, MISMATCH or NOT_FOUND, with the matching record. Errors (never charged): 400 bad input, 422 source could not be fetched or parsed, 429 rate limited (30/min), 502 upstream failed.

Look up a product by EAN/UPC barcode in Open Food Facts, Open Beauty Facts and Open Products Facts: name, brand, quantity, categories, ingredients, allergens, labels, nutrition per 100 g, Nutri-Score, NOVA group and image URL. Params: barcode (8 to 14 digits, required).

Drop-in Exa-compatible search: the same request (query, numResults, category, includeDomains, excludeDomains, startPublishedDate, contents.text, contents.highlights) and response format (results with id, title, url, publishedDate, author, score, text, highlights) as Exa /search, on Google-quality authority-ranked results, $0.006 with page text included (Exa: $0.007 + per-page fees; resellers $0.01). Not affiliated with Exa.

Fetch a public web page and return just the main article as clean Markdown, with title, byline and excerpt. Menus, ads and footers are removed. Use when you need to read, summarise or quote a web page cheaply without parsing HTML yourself. Returns JSON {title, byline, siteName, excerpt, markdown}. Errors: 400 bad or private URL, 422 no readable article, 502 site returned an error.

Alt text for images, for web accessibility (WCAG 1.1.1, BFSG, European Accessibility Act) and SEO: send image_url or image_base64, get alt text under 125 characters that describes purpose and content, a longer description for complex images such as charts, whether the image is decorative (then alt=""), all readable text in the image, and a ready alt="..." attribute. Optional language (e.g. German) and context (where the image is used).

Check whether a website is up right now: HTTP status, response time in ms, full redirect chain, and the SSL certificate's validity, issuer and days until expiry. Use when monitoring a site, diagnosing a broken link, or warning that a certificate is about to expire. A site that is down still returns 200 with up:false and the error. Errors: 400 bad or private URL.

Currency exchange rates (European Central Bank reference rates) for price conversion, invoicing and travel budgets. Latest or historical by date.

Find public dataset catalog entries in GovData (Germany) or open.bydata (Bavaria): titles, short descriptions, publisher, source/identity links, source modification date, per-resource license references and access/download links. One catalog GET, up to 10 datasets; never downloads the actual source files. No API key needed.

Public holiday calendar for 100+ countries by year, for scheduling, payroll and delivery planning.

Business day calculator for SLAs, invoice due dates, shipping and legal deadlines: counts working days between two dates, skipping weekends and national public holidays (ISO country code).

Domain registration lookup via RDAP (modern WHOIS). Returns registrar, registrar_url, created_at, updated_at, expires_at, days_until_expiry, name_servers array, status array, and registrant_country. Clean JSON, no raw WHOIS text to parse. Covers all major TLDs.

Query onchain DEX token price & market data based on the provided token contract addresses on a network.

Find a French company's SIREN from its name, optionally filtered by postcode or INSEE commune code. Returns up to 10 matches (name, status, NAF code, city, creation date), no personal data. First step before KYB / supplier verification of a French company.

Summarize any web page: send a URL, get a factual summary that starts with what the page is, followed by the key facts, numbers and conclusions as bullet points. Reads the page (HTML to Markdown) and summarizes it with Claude Haiku 5.5. Options: length short (60 to 90 words), medium (150 to 220) or long (350 to 450); language for the summary (default: the page language, e.g. German); focus to steer it (e.g. "pricing and plans").

Security advisories: Known exploited vulnerabilities (CISA KEV) enriched with daily FIRST EPSS exploit probability. Use when a user asks whether a CVE is actively exploited, which vulnerabilities in a vendor or product to patch first, whether it is used in ransomware campaigns, or needs CISA KEV due dates, required actions and FIRST EPSS exploit probability in one call.

Find the right paid API for a task across the whole x402 market, not only agentsvc.io: describe what your agent needs in plain words ("convert a web page to markdown", "token price on Solana", "transcribe audio") and get the best matching x402 endpoints from about 45,000 listed ones, each with provider, URL, method, price in USD, payment networks, an input hint, and whether it answered our own check with a valid 402 (reachable, checked_at, response time).

IP address lookup for security triage, log analysis and fraud checks: owning network, allocation range, registry country (RDAP) and reverse DNS.

IP lookup and geolocation: resolve any public IPv4 or IPv6 address to location and network data from a local database (no third-party call, answers in milliseconds): country, country_code, region, city, lat/lon, IANA timezone, continent, is_eu, ASN with organization (isp, org, asn). Use for fraud and bot checks, geo-routing, analytics, or tagging traffic. Invalid, private and reserved addresses are rejected for free. Params: ip (defaults to the caller's IP).

Look up a PyPI package: latest version, license, summary, required Python version, dependency count, homepage, and release count. One call, structured JSON. For Python dependency analysis and package vetting.

Read 2 to 5 pages whose URLs you already know in one call, each as clean Markdown with title and description, fetched in parallel. Cheaper and faster than calling web-scrape once per URL; for 6 to 20 URLs use web-scrape-batch. A failed page is reported with its error while the others still return; charged only if at least one page was read. To find URLs first, use site-map (one site) or search-read (a question). Params: urls (1 to 5, required), max_chars per page (500 to 30000, default 6000).