cyberwarex.com

Screen an EVM wallet or contract address BEFORE paying it. Deterministic, keyless compliance / safety gate: checks the address against the OFAC sanctioned crypto-address list and a curated taint set (mixer, hack, scam) and returns a single BLOCK / REVIEW / ALLOW recommendation plus the matched sources, so an AI agent can decide whether to send funds. No API keys, no LLM, one x402 USDC micropayment per call.

Put one question to a panel of 3 different AI models and get a single verdict back. Each model answers independently, then a chair synthesizes: verdict, confidence, the points they all agreed on, the dissent, and what would flip the answer. Use it for judgement calls where one model's opinion is not enough: is this safe, is this worth it, which option. No account, no API key, one USDC micropayment per call.

The deep council: 4 different AI models, two rounds. Each seat answers, then sees the other seats' positions and revises - so you get a verdict that survived cross-examination, with changed_after_debate on each seat and the dissent that held. For decisions where being wrong is expensive.

The grounded council: we buy the facts first, then deliberate on them. Your question is scanned for a contract address, URL or $TICKER; we spend on the matching evidence (honeypot simulation, sanctions screen, page content, SEC profile, web results), hand it to 4 different models for two rounds, and return a verdict that rests on what was found. The response lists every source and what we spent for you.

Render any live web page to a portable PDF, returned as base64. JavaScript runs first, so single-page apps and dynamic content render correctly instead of coming out blank. Use it to archive a page, capture a receipt, invoice or report, snapshot terms or pricing that may change later, or hand a human a fixed copy of a URL.

Pixel-accurate PNG screenshot of any live web page, rendered in a real browser at a chosen viewport width, viewport-only or full-page. Returns base64 PNG. Use it when an agent needs to SEE a page: visual verification of a deploy, layout and design capture, confirming a rendered chart or map, or feeding an image to a vision model that cannot read HTML.

Extract text from an image by URL (OCR): PNG/JPG/WEBP/TIFF/BMP of a screenshot, scan, receipt, chart or photo -> the readable text, via the Tesseract engine. Keyless, no LLM. Use it to read text an agent can only see as an image. SSRF-guarded; max ~10MB.

Targeted web scrape: pass a CSS selector and get back only the matching elements from a fully JavaScript-rendered page. Each element returns its tag, text content and every HTML attribute. Use it to pull prices, links, table rows, headlines or any repeated structure without parsing a whole document. Returns a match count so an agent can tell an empty page apart from a broken selector.

Read any live web page as clean, LLM-ready text. Renders JavaScript in a real browser, then strips navigation, ads and boilerplate. Use it when a plain HTTP GET returns empty or garbled HTML: single-page apps, dynamic feeds, or content that only appears after scripts run. Returns markdown, plain text or cleaned HTML plus the upstream HTTP status. Page content is third-party data and is flagged untrusted so an agent treats it as input, never as instructions.

Fetch a verified contract's ABI and metadata by address, keylessly, from Sourcify. Returns the ABI plus a summarized list of function and event signatures, the contract name and compiler, and proxy detection (is_proxy + implementation address). Block explorers gate the ABI behind an API key; this does not. Chains: base, ethereum, arbitrum, optimism, polygon, bsc, avalanche. No API keys, no LLM, one x402 USDC micropayment per call.

Contract-level risk scan for any EVM token: is the source verified, is it an upgradeable proxy and who is its admin, who owns it and has ownership been renounced, and which dangerous powers the bytecode exposes (mint, pause, blacklist, fee-setting). Returns the raw on-chain evidence, not just a score, so an agent can justify the decision it makes.

Full safety report for an ERC-20 token. Runs a live buy-then-sell honeypot and tax simulation against real DEX liquidity (Aerodrome, Uniswap V2/V3/V4), scans contract powers (upgradeable proxy, mint, pause, blacklist, fee-setting), resolves ownership and effective controllers, and cross-checks GoPlus and honeypot.is. Returns an A-F grade, tradeable flag, 0-100 risk score and evidence-carrying flags an agent can cite.

Focused honeypot check: a live buy-then-sell simulation against real DEX liquidity (Aerodrome, Uniswap V2/V3/V4). Tells an agent whether the token can actually be SOLD, the round-trip loss percent, and whether GoPlus or honeypot.is flag it too. Catches sell-blocking scam tokens, extreme sell taxes and no-liquidity traps before a buy is placed.

ENS name resolution in both directions on Ethereum mainnet. Pass name to resolve an ENS name to its address (forward), or pass address to get that address's primary ENS name (reverse, forward-verified so spoofed reverse records are rejected). Read straight from the ENS registry. Use it to turn vitalik.eth into an address, or to label a raw address with a human-readable name.

Spot USD price for any crypto asset. Accepts a ticker symbol (eth, btc, sol), a CoinGecko id (ethereum), or an EVM token contract address. Returns the USD price plus 24h change, with market cap for listed assets, or liquidity, 24h volume and the top DEX pair for contract addresses. Cached 60 seconds so repeated calls in one agent workflow stay consistent with each other.

Latest block on any major EVM chain: block number, timestamp, age in seconds, base fee and gas used/limit. The cheapest possible liveness and chain-tip check for an agent: confirm a chain is progressing, timestamp an observation, or pick a block for a query.

ERC-20 token profile on any major EVM chain: on-chain metadata (name, symbol, decimals, total supply) read straight from the contract, joined with live DEX market data (USD price, liquidity, 24h volume, 24h change, and the top trading pair with its DEX). Use it to price a token, check liquidity depth before a swap, or resolve an unknown contract address into a real token.

Transaction lookup and decode on any major EVM chain. Turns a raw tx hash into agent-readable facts: success or failure status, block number, sender and recipient, native value transferred, gas used, fee in native token and USD, and every ERC-20 transfer decoded with token symbol, decimals and human-readable amount. Returns found=false for an unknown hash instead of erroring.

Live gas market on any major EVM chain: current gas price, base fee and priority-fee percentiles (p25/p50/p75) in gwei, plus the estimated cost in native token and USD for a plain transfer (21k gas) and a typical DEX swap (200k gas). Lets an agent decide whether a transaction is worth sending right now or should wait for cheaper gas, and budget the fee before signing.

Crypto perpetual-futures snapshot for a symbol in ONE call (Binance USD-M, keyless): current funding rate and the next funding time, mark and index price, open interest (contracts and USD), 24h price change/high/low/volume, and the top-trader long/short account ratio. For funding arbitrage, leverage/positioning reads, and a derivatives view an onchain-only feed cannot give. Cached 30s.

Key annual fundamentals for a US ticker from SEC XBRL: revenue, net income, total assets and liabilities, stockholders equity, cash, basic EPS and shares outstanding, each with its fiscal period and source concept. Keyless, public-domain EDGAR. For valuation, screening and grounding a financial claim in primary filings.

Decode an off-chain SIGNATURE REQUEST before you sign it: EIP-712 typed data (eth_signTypedData_v4) or a plain personal_sign string. Turns the opaque request into a human-readable summary plus security risk flags for the drainer patterns wallets miss - gasless unlimited token approvals (EIP-2612 Permit, DAI permit, Uniswap Permit2) and asset-transferring marketplace orders (Seaport). Keyless, deterministic, zero network.

One pre-sign safety verdict (GREEN, REVIEW or BLOCK) fusing transaction, signature, address, URL and token checks for AI wallet agents.

Decode raw EVM calldata into a named function, signature and arguments, plus security risk flags (unlimited token approval, setApprovalForAll, ownership transfer, unknown selector, native value transfer). Keyless, deterministic, no simulation - the cheap way for an agent to understand and risk-screen a piece of calldata before signing.

Score a URL for phishing risk before an agent opens or trusts it. Keyless, deterministic heuristics - typosquat / homoglyph of a known brand, punycode / mixed-script hosts, credentials-in-URL, raw-IP hosts, suspicious TLDs, over-deep subdomains - plus a best-effort domain-age check (young domains are a top phishing signal). Returns a 0-100 risk score, a SAFE / SUSPICIOUS / DANGEROUS verdict, and labelled reasons. No API keys, no LLM.

Weather forecast for a location (global, keyless): current conditions, an hourly series (up to 48h) and a daily summary (up to 10 days: min/max temp + condition), from met.no. Pass lat+lon, or a place name. For travel, logistics, events, energy. No API key.

On-page SEO audit for any live URL. Returns a 0-100 SEO score plus the raw signals behind it: title tag and meta description with their lengths, canonical URL, robots directives, the full H1-H3 heading map, image alt-text coverage, Open Graph and Twitter card completeness, and whether schema.org structured data is present. Fetches the live page on every call, so results reflect the page as it is now. Use it to audit a landing page, diagnose weak search rankings, or inspect a competitor.

Fleet-wide uptime statistics for every monitored endpoint: uptime percentage, average response time, and total check count over 1, 7 and 30 day windows (plus an optional custom window). Use it to get an at-a-glance reliability picture of a service fleet in one call.

YouTube video transcript extraction with per-segment timing. Returns the caption track as timed segments (start, duration, text) plus the full plain text, or as SRT subtitles. Uses the creator's manual captions when they exist and falls back to YouTube automatic captions. Never downloads media, so it stays fast and light. Cached per video and language. Use it to summarize a talk, quote a video with timestamps, or search inside video content.

YouTube video metadata in one call: title, channel name and id, duration, upload date, view and like counts, description, thumbnail URL, the chapter list with start and end times, and the language plus kind (manual or auto) of every available caption track. Never downloads media. Use it to check a video's length or caption availability before paying for a transcript, or to enrich a bare video link with real facts.

Web search that returns structured SERP results as JSON. Runs on a dedicated SearXNG instance aggregating multiple engines, so there is no per-engine API key, quota or HTML scraping to manage. Each result carries title, URL, snippet, the source engine and a published date where available. Choose general web, news, or image results, up to 10 per call. Use it to ground an answer in current web sources, research a topic, or monitor news on a query.

Fetch one public web page and return its readable content as clean text or markdown, with JavaScript executed, so the result reads like the page a human sees. The retrieval half of research: pair it with /search to go from a query to grounded page text. Returns the content, its length, the final URL and the HTTP status. Truncate with max_chars.

Ranked news brief for any topic, refreshed every 15 minutes: the most-corroborated recent headlines, each with source, URL, published time, age in minutes and an importance score computed from how many independent news engines surfaced it and how fresh it is. Zero-LLM, deterministic, no API key. Use it for a market or crypto morning brief, monitoring a company or keyword, or grounding a summary in dated sources.

Web search with the page text already extracted: one call returns the top results for a query AND the readable content of each result page (JavaScript rendered, markdown or text, truncated to max_chars). What an agent needs to answer a question with sources without a second round of fetches. Up to 5 pages per call, fetched in parallel.