Web & Data

Search the global corpus of published fact-checks (ClaimReview) by free-text claim. Returns matching claims with the claimant, claim date, and each fact-check review's verdict (textualRating, e.g. "False", "Misleading", "True"), the publisher (PolitiFact, Snopes, FactCheck.org, Reuters Fact Check, AFP, …), the review URL, and review date. Covers every topic — politics, health, science, viral and misinformation claims. Optional language, recency (maxAgeDays), and publisher-site filters. Aggregated by Google from publishers' schema.org ClaimReview data. Use it to check whether a claim has been independently fact-checked and how it was rated, rather than asserting from training data.

Look up a CVE by id (e.g. CVE-2021-44228) across three authoritative vulnerability feeds in one call. Query: cve (CVE-YYYY-NNNN). Returns the canonical record — description, CVSS base score + severity + vector, CWE weakness ids, published/modified dates, reference links — plus whether it is on the US CISA Known Exploited Vulnerabilities catalog (with remediation due date and known-ransomware flag) and its EPSS exploit-probability score and percentile. The exploited and EPSS sections report independently, so one feed being unavailable does not fail the call. 404 if the CVE id is unknown. For triage, prioritization, and anti-hallucination on vulnerability claims.

Evaluate trust of a domain, URL, wallet address, or API endpoint. Returns composite score 0-100 with grade (A+ to F), verdict (trusted/moderate/suspicious/dangerous), and 5 detailed sub-scores.

Neural web search for agents (Exa upstream): pass a query, get the most relevant live web pages with title, URL, published date, author, relevance score and a clean text snippet as structured JSON. The find-then-read pair for /web-extract — RAG retrieval, research, fact-finding, monitoring. Keyless, pay-per-call, cached by query. A no-match query returns an empty result set as a valid answer.

Render a URL in a real headless browser (JavaScript executed) and return its article content with the clutter stripped — same cleaning + output formats as /api/url/clean, but for client-rendered / SPA pages whose content only appears after JS runs (where a raw HTTP fetch returns an empty shell). `format`: markdown (default), text, both (JSON envelope), html (self-contained reader page, raw text/html), or pdf (typeset reading doc, raw application/pdf). Optional `waitUntil` (load|domcontentloaded|networkidle0|networkidle2, default networkidle2) and `timeoutMs` (1000-15000, default 12000) control how long to let JS settle. Use /api/url/clean instead for server-rendered pages — it is faster and cheaper; only reach for render when JS rendering is required.

Fetch and parse a domain's robots.txt file — returns all crawl rules by user-agent, sitemap URLs, crawl delay settings, and checks whether a specific path is allowed or blocked for any bot — so agents can respect crawl policies and locate sitemaps before scraping.

US electricity grid — demand, generation mix (renewable/gas/nuclear), and stress signals across 7 regions

AI web search optimized for agents. Returns ranked results with the relevant extracted content of each page (not just a link + blurb), plus a relevance score. topic=news for recent reporting. Distinct from search.web (raw SERP) — this returns clean, LLM-ready page content per result.

Classify text content into categories with confidence scores and readability metrics

Signed extractability score (0-100) + breakdown + fixes for a URL

MSVI Ethereum volatility index — composite of realized vol, implied vol, term structure, funding stress and put/call ratio — Ed25519 signed attestation

MSVI Bitcoin volatility index — composite of realized vol, implied vol, term structure, funding stress and put/call ratio — Ed25519 signed attestation

Extract structured text, tables, and metadata from any PDF URL. Returns page-by-page text content, detected tables as JSON arrays, and document metadata (title, author, page count). No PDF library or OCR setup needed — pay per extraction. AI agent API for document intelligence and data extraction

Search ArXiv for academic papers and preprints in AI, machine learning, CS, and mathematics. AI agent API for scientific research. Accepts USDC payments on Base and Solana

Search code across GitHub with the code-search syntax (e.g. 'defineEndpoint repo:AlleyFord/2s' or 'addEventListener language:js'). Returns total match count + file name, path, repository, and URL for each hit. Read-only; no caller key needed.

Geolocate a single IPv4 or IPv6 address. Returns country (name + ISO code), region (name + code), city, ZIP, lat/lon, timezone, ISP, organization, and AS number + name. For bulk lookups (up to 100 IPs in one call) use /api/ipinfo/bulk instead. Lat/lon precision is city-level, not GPS.

List a repository's releases: tag, name, draft/prerelease flags, author, published time, and release notes body. Paginate. Track a project's version history. Read-only; no caller key needed.

Resolve a song/recording from MusicBrainz (the open, CC0 music encyclopedia). Pass artist + title, or a free-text query (Lucene supported). Returns ranked recordings with MusicBrainz ID (MBID), title, primary artist, length (ms), first-release date, and disambiguation. Keyless, public-domain core data. Use to canonicalize a track to its MBID or cross-reference identity.

List pull requests for a repository: number, title, state, author, draft flag, merged status + time, head/base branch, and created time. Filter by state (open/closed/all); paginate. Read-only; no caller key needed.

Search GitHub repositories with the full query syntax (e.g. 'x402 language:typescript stars:>100'). Sort by stars/forks/updated. Returns total match count + repos with stars, language, topics, license, timestamps. Read-only; no caller key needed.

Search the US Federal Register — proposed rules, final rules, notices, and presidential documents. Filter by free-text term, document type (RULE/PRORULE/NOTICE/PRESDOCU), agency slug (e.g., epa, fda, sec), and publication date range. Returns document_number, type, title, abstract, FR citation, agencies, publication_date, effective_on, comments_close_on, htmlUrl, pdfUrl, rawTextUrl. Public-domain US government data. Real-time — published daily, past LLM training cutoff.

Fetch a repository's README, decoded to UTF-8 text (name, path, size, content, URL). Optionally pin to a branch/tag/sha via ref. Useful for summarizing or indexing a project. Read-only; no caller key needed.

A single Polymarket market by conditionId, slug, or id. Returns the question, outcomes + live prices (implied probabilities), CLOB token ids, USD volume + liquidity, dates, description, and URL. Pass one of conditionId / slug / id.

MLB games for a date (and optionally one team), via the official MLB Stats API (free/keyless). Each game: gamePk, start time, detailed status (Scheduled/In Progress/Final), away and home team + score, and venue. Defaults to today when no date is given. Live scores + schedule for agents.