Fetch one web page and return its main content as clean Markdown with title and word count, extracted server-side. Private and loopback targets are refused. Use this when an agent needs to read a page inside a workflow without a browser and without wading through navigation and boilerplate.

Decode one Base transaction into plain English: sender, receiver, ETH value, status, the known method behind the selector, every ERC-20 transfer it made, and a one-sentence summary. Use this when an agent needs to explain or verify what a transaction actually did before acting on it.

Detects the dominant language of a text (over 100 languages) with Amazon Comprehend, from its first 1000 characters. Returns the most likely language codes with scores.

Change detection for anything with a URL, built for monitoring loops: probe one x402 resource or web page WITHOUT paying it and answer BASELINE, UNCHANGED, or CHANGED with a field-by-field diff (price, asset, payTo, schema, page body) against the last check for that watch. Use this when an agent runs on a schedule and needs to know what changed before spending money or attention. Watch and pack state persist across redeploys on the service volume. Packs: $1 for 250 checks on one endpoint.

Audit one Base wallet's ERC-20 approvals against a curated list of major spenders (Permit2, Uniswap, Aerodrome, aggregators): active approvals are listed and unlimited ones flagged high risk. Use this when an agent or its owner wants to know what a wallet has already authorized before it holds or moves funds. When the explorer cannot supply the held-token list, the token-dependent fields come back marked unknown rather than the call failing.

Snapshot one Base wallet in a single call: ETH balance, top token holdings, first and last activity, and outgoing transaction count. Use this when an agent needs a wallet's shape before deciding to pay, trust, or transact with it. Explorer fields that cannot be supplied come back marked unknown, never invented.

Send any x402 resource URL, get a trust verdict on the endpoint itself. Returns TRUSTED / CAUTION / AVOID with a 0-100 score from an observation-only live probe (never pays the target): payment terms, Bazaar discovery-schema quality, CDP Bazaar and PayAI catalog presence, plus a diff against the previous check. Use this when an agent is about to pay an unfamiliar x402 endpoint and needs to know it is alive, honestly described, and unchanged first.

Send a token contract address, get a risk verdict. Returns SOLID / CAUTION / DANGER with a 0-100 score, six weighted market-structure signals (liquidity depth, volume churn, sell pressure, price action, trader breadth, pair age) and a written analyst take. Built for AI agents screening tokens before touching them. Use this when an agent is about to buy, swap, or route funds into a token and needs a fast risk screen first.

YouTube search results as clean JSON: title, video id, URL, channel, duration, and views for each result, scraped from the public results page with no API key. Use this when an agent needs to find a video mid-task and cannot drive a browser or hold a Google API key.

Get the full text of one web page. Give a URL; returns the page's own main content as clean markdown (up to 8,000 characters) with navigation and ads removed, unchanged and not summarized (use /summarize for a short version). Typical response 2 to 5 seconds. If the page cannot be read you get an error and are not charged.

Preflight one public Apify Actor before a paid automation run using only public Store and default-build OpenAPI metadata. Forest checks agentic-payment eligibility, pricing/budget signals and top-level input compatibility without starting an Actor, buying credit, authenticating or making an external payment. Base mainnet USDC

Watch one field on a web page for 30 days, e.g. a price, stock status or version number: it is read again every 15 to 1440 minutes and an alert goes to your webhook, Slack, Discord or Telegram when it changes, goes below or above a number, contains a text, or disappears. Returns the current value now; check status or stop it for free with the watch secret.

Check a Base token before your agent buys it, via Liquid Logic X: send an ERC-20 address, get risk (low/medium/high), score, flags and evidence: owner, upgradeable proxy, mint/blacklist/fee/pause powers in code, owner and burn %, DEX liquidity, pair age, 24h buys vs sells, X-Lock locks. $0.01 USDC on Base.

Inspect the declared request and response contract for one exact OpenAPI or Swagger operation before integration. Returns parameters, request-body content types, response statuses/content types and declared security scheme names without executing the endpoint or resolving external references. Base mainnet USDC

Multi-asset USD price snapshot in ONE call (10 majors default) — batch beats per-pair calls

Token verdict — is this Base token safe to buy? Call this token safety and rug check first: should I buy this token? Verdict BASED/MID/COOKED/RADIOACTIVE + action ENTER_OK/CAUTION/SKIP + confidence + red flags + expected loss for your amount, from live pool liquidity, volume, holders, honeypot and owner checks. Shareable verdict page in every call. No API key

Normalize the latest public GitHub Actions workflow/run state. Reads only; dispatch, rerun, cancellation, private repositories and customer OAuth are unsupported. Base mainnet USDC

Uptime SLA for an AI agent: uptime percent, latency p50/p95 and flap counts. Check before you rely on it or route work to it

Base ERC-20 risk verdict (OK / CAUTION / AVOID) for $0.01: simulated sell and taxes, top-10 holder share, pool liquidity and age, LP burn, verified source, mint/blacklist functions. Pass a token address.

Validate and normalise an NZ phone number to E.164 with type