All services

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. Typical agent tasks: check for a large exchange inflow on Base, monitor bridge flows into or out of a chain, track stablecoin issuer mint or burn events, or add on-chain flow context to a crypto market-intelligence pipeline. Configurable 1-168 hour lookback, USDC on Base via x402.

Detect private/loopback IPv4. Call when you block private egress targets in agent allowlists. Returns valid and private flags 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.

Is this token active right now? Live pulse of any ERC-20 on Base: transfer count, volume and unique senders/receivers over a recent block window — one call, no RPC or indexer needed. ?token=0x...

Reads the holders of an LP token and splits them into burned, locked in a named locker, and free. Burned and locked are two different things and are reported separately - burned is gone for good, locked comes back. A locker contract that is not in the curated table yields is_locker "unbekannt" rather than false, because an unknown lock contract is not the same as a demonstrably free holder. Limits: earliest_unlock_ts is NOT read - the unlock time lives inside each locker contract in its own layo

Derives behaviour classes from on-chain activity: share of swaps, regularity of intervals, hour-of-day spread, counterparty count and contract code. Several classes at once are allowed and usually more accurate than one. Every class carries its evidence; without evidence no class is set. automation_likelihood comes from measurable traits - interval regularity and how evenly activity spreads over the day - listed in features_used, never from a hunch. Limits: this classifies BEHAVIOUR, not people.

Returns the hazard profile of a chemical: GHS pictograms, signal word, hazard statements and precautionary statements where they are recorded, together with the physical properties that govern handling — melting and boiling point, flash point, density, vapour pressure, solubility and autoignition temperature. Every statement carries the organisation that contributed it, and that attribution is the substance of the service rather than a citation courtesy.

Reads token balances of one wallet on several chains from a public index and the native balance from the node itself. The same asset exists on several chains in different versions; canonical and bridged issues are reported separately and still summed, because both together are the answer. Every chain carries its block height, without which the sum cannot be checked. A chain that cannot be reached drops out with a reason under chains_failed and the call stays valid. Limits: the index exists for E

Computes the growth of coverage for a topic between a recent window and a baseline, and reports the spread across languages and publishing countries alongside it. The spread is the more informative half: a topic exploding in one language is a national event, one rising simultaneously across eight languages is something else entirely, and a growth rate alone cannot tell them apart.

China industrial-theme momentum: which Chinese tech/industrial narratives (AI compute, semiconductor localization, robotics, defense, new energy) are heating up — aggregate rotation strength + per-Shenwan-board rotation score, rank, trend, lifecycle phase (emerging/sustained/fading), English-labeled. Quant structure, no news text. What China is betting on in tech, for global investors' agents. Query: ?tag=ai|semi|robot|defense|new_energy (optional filter).

Reads token movements of a wallet, prices every inflow and outflow at the time it happened, and derives cost basis, realised and unrealised profit or loss per asset. The method is stated because the result depends on it. Uncertainty is a mandatory field, not a footnote: an on-chain history knows nothing about deposits from exchanges, transfers between wallets of the same owner, or assets no price source covers. coverage_pct says which share of the movements carries a price; below sixty percent t

Significant earthquakes — search USGS seismic events above an explicit significance-score threshold, with magnitude and provenance but no danger or probability claim.

Paddock niche gap analysis — one-time query

Nearby Citi Bike pickup stations with available bikes and e-bikes

Active subway service alerts with direction, severity, and estimated delay minutes

Returns the main trading partners of a country for exports and imports, each with its share, and the concentration of that distribution measured by the Herfindahl-Hirschman index over partner shares. Concentration is the measure that carries the signal: a country sending thirty percent of exports to one state with the rest spread over twenty others is exposed differently from one sending thirty percent to one state and sixty to a second, and the largest partner is identical in both cases.

Aggregates medical device reports for a product code, device name or manufacturer into a trend: reports per year, the split between malfunction, injury and death outcomes, the most frequent problem codes, and the share of reports where the manufacturer conducted an evaluation. Two things the figures are not, and both are stated in the response rather than left to be inferred.

Assembles a macroeconomic profile of a country from World Bank indicators, and refuses to present it as a snapshot of one year. Official statistics arrive on different schedules: real GDP growth may be current to last year while a labour force figure lags by three, and a profile that omits this silently blends half a decade into what looks like a single reading.

Reports the credit-to-GDP gap for a country, which is the deviation of the credit ratio from its long-run trend and the quantity the Basel framework uses to trigger the countercyclical capital buffer. The thresholds applied are the regulatory ones — the buffer starts to build at a gap of two percentage points and is at maximum by ten — and they are returned with the result, because a phase judgement built on invented cut-offs is an opinion while one built on the supervisory thresholds can be…

Returns annual gross earnings and hourly labour costs per country, in national currency or euro and in purchasing power standards, and never blends the two. The separation is the point: forty-five thousand euro in one country and twenty-two thousand in another is a factor of two nominally and much less in purchasing power, and which figure is correct depends entirely on the question.

Assesses the recorded biodiversity of an area around a point: how many distinct species appear, how many records support them, how recent those records are, how many separate datasets contributed, and the breakdown by kingdom. The trap this service is built around is that record density measures observers, not organisms — a city park with heavy footfall carries more records than a roadless reserve and is not thereby richer.

Summarises adverse event reports for a drug: the most frequently reported reactions, the distribution of serious outcomes, the split between reports from health professionals and consumers, and the trend over time. Three limitations are returned with every response and are not footnotes. A report establishes that somebody suspected a connection, not that one exists — the system records suspicion, not causation.

Combines the unemployment rate, the job vacancy rate and the activity rate for one or more countries into a tightness assessment. The measure that carries the signal is the relation between vacancies and unemployment, not the unemployment rate on its own: four percent unemployment alongside a high vacancy rate means employers cannot find people, and the same four percent alongside a low vacancy rate means there are no jobs, and those are opposite situations that the headline rate reports…

Returns harmonised consumer price inflation for several countries over a period, taken entirely from the European harmonised index so the numbers are actually comparable. That constraint is the product: national consumer price indices use different baskets, treat owner-occupied housing differently and rest on different base years, so placing them side by side produces a comparison that looks valid because everything is expressed in percent and is not.

Takes any identifier for an EU legal act and returns the others, along with the available language versions and formats. The distinction it insists on is the one that is constantly confused: the work is the act itself and is language-independent, the expression is its version in one language, and the manifestation is a file of that expression.