Every agent-payable API.

Weather forecast API: current conditions (temperature, feels-like, humidity, wind, weather code) plus a 3-day daily forecast (highs, lows, precipitation probability) for any latitude/longitude worldwide, as structured JSON. Use for travel planning, logistics, event scheduling, and assistant agents. Cached 10 minutes.

Paid compressed relationship map connecting solar energy, atmospheric circulation, water cycling, jet streams, clouds, storm systems, local weather, regional weather patterns, and Earth systems.

Paid machine-readable Weather registry connecting the water cycle, atmospheric circulation, jet streams, storm systems, clouds, weather patterns across scale, pattern formation, the Naturepedia Weather Mesh, and future weather observation.

Web search via a self-hosted SearXNG instance (title/url/snippet per result).

Web article and PDF to Markdown converter API - fetch any public URL and get clean Markdown plus title, byline, site name, excerpt and word count. HTML is extracted with Firefox reader-mode rules (Readability); PDFs return their text layer with page count. Honest failures: image-only PDFs return no_text_layer, client-rendered app shells return not_extractable - never an empty page passed off as the article. For AI agents, research pipelines, summarizers and content ingestion.

Web content extraction: fetch any public web page and get its readable article content as clean markdown — boilerplate, nav, and ads stripped automatically. For "get me the readable text of this page" requests. Honors robots.txt and Content-Signal/aipref declarations (explicit disallow returns an unpaid 403). SSRF-guarded, 2MB cap.

Deterministic bounded HTML structure extraction for a public URL.

Web extraction for AI agents: URL to clean Markdown + metadata, automatic JS rendering, robots.txt respected. No API key.

Read any public web page and get a clean LLM summary in ONE call — fetch, boilerplate removal, and Claude summarization fused. Query: url (public http/https); instructions? (optional steer, e.g. 'focus on pricing', <=200 chars). Returns {url, title, summary, word_count}. Replaces a scrape->prompt->parse pipeline with a single flat-price call.

Web content extraction for agents at the lowest price in this catalog tier: pass a URL, get the readable content as clean markdown or plain text - title, author, date, main text, tables, links. Direct fetch, no third-party search index resold. 3 MB / 20 s caps, internal addresses refused. Fixed $0.003 per fetch, signed receipt included.

Web scraping / URL fetch: retrieve any web page and return clean, LLM-ready markdown text. Strips boilerplate, ads, and navigation. Stealth HTTP client bypasses common bot blocks. Cheapest way to read a webpage.

Fetches and scrapes the URL provided in the `url` query parameter, then returns the original URL, the scrape timestamp, and a `scraped_data` object containing extracted page content and metadata.

Live web search for agents that hold no search account. Query: q (required), count (1-20, default 10), country (2-letter, optional). Each result: title, url, snippet. Fresh per call — search is a poll, not a cache. One account rented per query.

Web search (Google results via Serper): top 10 organic results + answer box + knowledge graph. Query: ?q=&gl=&hl=

Web search API - free-text query to ranked organic results, each with title, real destination URL, display URL and snippet. Sponsored rows are excluded. Returns up to 25 results; count is a maximum, not a guarantee, because a row whose destination cannot be resolved is dropped rather than guessed at. Results are not fetched or verified, and the response says so. Pair with /markdown to turn any result URL into clean Markdown.

Web search API — search the web and get clean ranked JSON results (title, url, snippet) via Serper with automatic Brave failover and cross-provider dedup. Optional cited answer. Input: { query, num? (1-20), answer? (bool) }.

Web search for agents: a query returns ranked title/url/snippet results (no API key, no signup)

Web search with structured results - title, URL and snippet - ready for agent consumption. Fresh results in one POST. Pay per call with USDC (x402) or credits - archtools.dev

Web mentions of a brand or keyword with source page and sentiment (Content Analysis index)

Search reusable Web3 and blockchain icons plus SVG and Lottie JSON animations for MPC, secret sharing, signing, and key recovery.

Extract structured metadata from any URL: page title, meta description, Open Graph and Twitter Card tags, canonical URL, favicons, language, generator and robots directives, plus RSS/Atom feed links. Give it a URL, get back clean SEO and social-share metadata. No account, no API key — pay per call with x402.

WEBSITE SCREENSHOT — render any public URL in a real browser and get the pixels. GET ?url=… returns a PNG as base64 JSON (add &raw=1 for the image bytes directly). Options: width 320-1920 (default 1280), height, full_page=1 for the whole scrolled page, format=png|jpeg. Ads and cookie banners are blocked automatically. For agents that need to SEE a page: visual QA, previews, archiving, design reference.

Fetch any public web page and return its raw text content — for agents that need to read live web data, docs, or articles. $0.001 per fetch. 💎【付款后立得】实时结构化JSON，即插即用——无需注册，USDC一键支付即取数据。

A durable inbound URL for agents that can't host a server. POST {ttl?} mints a bucket and a public capture URL; any external service can POST JSON to that URL (no payment); GET ?token= drains the queued deliveries. Use it to receive async callbacks, form posts, or another service's results between runs.

Webhook Signature Timestamp Check: Webhook Signature Timestamp Check checks webhook timestamp age and future skew before signature verification from bounded caller-supplied values without an external provider. Call Webhook Signature Timestamp Check before accepting, caching, redirecting, or retrying a caller-supplied web response. Returns normalized web evidence, the computed finding, and an explicit pass or advisory status for Webhook Signature Timestamp Check as versioned deterministic JSON.…

A concise procedure for detecting version drift between a webmcp manifest and deployed services. Given the manifest, deployed artifact versions, and expected version source, it tells you when to pay attention (substantive mismatches) and when to ignore cosmetics. Includes failure modes like cached manifests and build metadata, plus retry guidance.

Website Competitors API — the wedge: a computed top-competitors leaderboard (category rank + affinity score) plus similar/related sites with their own traffic and rank. Real-time, no login. SEO: competitor analysis API, similar websites API, competitive intelligence, market research API.

Track website changes over time for a specific company Pagination billing: call the first page normally and save billing.requestId from the Orthogonal /v1/run response. For later page, offset, or cursor calls on the same logical search, pass parentRequestId with unchanged non-pagination parameters. Valid continuation calls still get their own request IDs and quoted price, but are charged 0. Changing filters starts a new billable request.

Create a detailed research snapshot of a public website including metadata, headings, text, social links, emails, and external-domain analysis.

Website Traffic API — real SimilarWeb-grade traffic data for a domain: global/country/category rank, monthly visits trend, bounce rate, traffic-source breakdown, top paid keywords with CPC. Real-time, no login. SEO: website traffic checker, SimilarWeb API, traffic estimate API, domain analytics.

Weekday name from ISO date. Call when you label agent calendars without locale libs. Returns weekday and ok for $0.001 USDC via x402 on Base. No network, no keys, no retention; first-party local JSON only. Results are advisory; the caller owns budgets, auth, and production controls.

Weekend check for a date. Call when routing work, quiet hours, or business-day logic in agents. Returns whether the date falls on Saturday or Sunday. $0.001 USDC per successful call via x402 on Base—deterministic first-party JSON, no API key, no subscription, and nothing is billed on structured validation errors.

How close WETH lending on Base is to the kink where borrow rates explode — same contract as the USDC sensitivity route. Aave and Compound only; protocols without a readable curve are marked unmeasured, never assumed stable. Describes state, not a forecast. Verified per-asset accuracy is free at /accuracy.json; raw on-chain attestations at /track-record.

How much of the WETH lending APY on Base survives if incentives stop — same contract as the USDC durability route, for WETH. Undecomposable sources are named, never assumed incentive-free. Stress test of current readings, not a date forecast. Verified per-asset accuracy is free at /accuracy.json; raw on-chain attestations at /track-record.

Buyer-side MOVE/HOLD decision for WETH lending on Base — same contract as the USDC decision route, for WETH. Verified per-asset accuracy is free at /accuracy.json; raw on-chain attestations at /track-record.

Returns whale, CEX, bridge, and stablecoin flow alerts for a chosen chain and lookback window, each with direction, venue, and USD value — use it to catch large capital movements before they move price.

Large ETH transfers (>100 ETH) to and from known exchange wallets in the last 2 hours. Inflows to exchanges are potential distribution pressure, outflows suggest accumulation or a move to cold storage — but read them as context, not instruction: a single large transfer is often internal rotation between wallets of the same desk.

Large on-chain transaction monitor — whale movements on Base, Ethereum, and Robinhood Chain with AI pattern analysis

What it costs to hold a perpetual position: the venue's current hourly funding signed for your side, projected over your horizon in your own units, with the mark-to-oracle basis, open interest, and the assumption behind the projection stated rather than implied.

Whether buying discount points pays off: monthly savings from the rate buydown and the break-even month.

Which companies just received a federal subaward — and which are getting their FIRST one? Bulk feed over USAspending subawards (the File F prime→sub cascade), newest-first by action date: sub-recipient, prime, agency, amount (banded), NAICS, and date. new_only isolates first-time subawardees (no prime award on record) — the new-to-govcon growth signal. Flat rows, cursor-paginated up to 1000/page, filterable by state, NAICS, agency, minimum amount, or since. Observational public records as filed.

Which firms just received an FDA Warning Letter — an open compliance-gap and remediation clock? Bulk feed over the FDA Warning Letters index, newest-first by issue date: recipient firm, product area (drugs/devices/food/tobacco…), issuing office, alleged-violation subject, and the response / close-out clock. Flat rows, cursor-paginated up to 1000/page, filterable by product_area, subject, close-out state, or since. Observational records — an alleged violation, never an adjudication.

Which keywords a domain ranks for, with position, URL and search volume

Who actually owns a counterparty. Resolves a company to its Legal Entity Identifier and walks the GLEIF ownership graph — direct parent, ultimate parent and direct children — returning the group structure with the jurisdictions it spans. This is the entity-resolution step under every KYC, sanctions and diligence workflow: free lookups answer the name, almost nothing answers the group. Search by name and country, then resolve by LEI.

Who is trading a token on Uniswap, and which way. POST {token, chain?, limit?}. Aggregates a recent swap sample on the deepest venue by trader EOA and returns per-wallet buys/sells/volume_usd/net_token plus a stance (accumulator / distributor / accumulating / distributing). Wallets are profiling input — feed them to /agent/score to find out who is on the other side.

Domain registration facts over RDAP (structured WHOIS): registrar, creation and expiry dates, status codes, nameservers

Domain registration status, registrar, dates, and nameservers via RDAP (lite fields only)

WHOIS registration data for a domain: registrar, creation/expiry/updated dates, nameservers, status, DNSSEC, and organisation.

WHOIS-style registration lookup: created/updated/expiry dates, registrar, status codes, and nameservers for any domain, normalized from the authoritative registry into JSON. For "who owns this domain," availability checks, expiry monitoring, and security-screening agents.

Whois record for one domain: registration/expiry dates, registrar, status codes plus SEO metrics