Security

InboxGuards Email Test: Email address check: syntax, MX, disposable and role account (no SMTP probe). Checks one address without sending mail: RFC syntax, whether the do…

Dragons Eye Lookup: Ransomware leak-site claim lookup by company name or domain. Returns ransomware-group claims (group, dates, country, sector, sources) matching the co…

Dragons Eye Lookup: Newest ransomware leak-site claims, optionally for one group. Up to 10 of the newest ransomware-group claims, optionally for one group. Unverified cl…

U.S. Treasury auctions: recent results (high yield, bid-to-cover, indirect/direct/primary-dealer share) and upcoming auctions with size. Public-domain Fiscal Data. Marke…

Heuristic risk checks for a Base ERC-20: contract code, metadata, proxy, owner/renounced, mint/blacklist/pause/fee selectors, deepest Uniswap/Aerodrome pool, and simulat…

Miorail x402 paid resource

DeFi yields now ($0.002): best supply and borrow APY of every Aave v3, Spark and Compound v3 market on Ethereum, Base, Arbitrum, Optimism and Polygon, read on chain ever…

Batch trading decisions for up to 5 assets in one POST ($3): send {"symbols": ["ETHUSD", "NVDA"], "side": "buy"}; get each premium decision (action, conviction, pillars,…

Honeypot check for any token ($0.02): can it be sold after you buy? Simulated sell and buy on chain, owner and proxy, mint, blacklist, pause and fee functions, liquidity…

Rug check for any token ($0.01): is this token a rug pull or scam? Short verdict LOW_RISK, CAUTION or HIGH_RISK with a 0-100 safety score, one plain sentence, can it be…

Recommend evidence-bound hold or release states without custody or fund movement

Propose capped shadow prices without changing live prices

Identify capability shortages from verified demand and provider supply

Forecast only from verified demand windows with low-sample abstention

Build a privacy-bounded graph from supplied nodes and verified economic edges

Validate and bundle agent-bound receipt evidence without claiming external truth

Calculate a fail-closed maximum cost across an agent execution plan

Evidence-bounded reputation assessment with confidence, coverage and explicit limitations

Inspect untrusted tool output before it enters an agent context or triggers another action

Validate least-privilege capabilities, data scope, destinations, budget and expiry before agent-to-agent delegation

Screen persistent agent-memory writes for poisoning, missing provenance, secret requests and unsafe instructions

Bind a proposed tool call to declared intent, allowed tools, destination and cost before execution

Enforce declared per-call, task, session and period budgets before execution

Detect safe replays and conflicting reuse of an idempotency key