Measured rates at which web services lack machine-readable capabilities. Research demonstrator.
Scored across 5 tools
Each tool targets a distinct granularity: aggregate rate, time series, bulk paid detail, per-host findings, and bespoke requests. The only real overlap is between absence_rate (aggregate) and bulk_export (per-class numerators), though the descriptions make the free-aggregate vs paid-detail split reasonably clear.
All five names are lowercase snake_case, two-word domain-qualified nouns (absence_rate, adoption_curve, bulk_export, host_report, request_capability) with no mixed conventions. The absence of verbs is consistent across the whole set rather than erratic.
Five tools is tightly scoped for a niche measurement index: one per granularity tier plus an escape hatch. No tool looks redundant or bolted on.
The surface covers aggregate stats, trends, detailed export, per-host drill-down, and a request path for gaps — a solid lifecycle for a data product. A discovery/catalog tool enumerating available gap classes and their schemas would close the remaining gap, since users must already know class IDs like PH-C019.
Measured absence rate for a population, with the evaluated denominator and sample provenance. Pass gap_class (e.g. PH-C019) for one class; omit it for the whole table. Aggregate only: no per-host findings.
Inputs: gap_class.
Dated adoption series: share of sites whose robots.txt takes a stance on AI agents, by Common Crawl epoch, single vantage. Called with no arguments it returns the trend and the caveats, not the whole table. Pass epoch for one point, series: true for all of them, or withheld: true for the undersampled epochs that are kept out of the series. Caveats are always included — read them before quoting a number.
Inputs: epoch, series, withheld.
Per-class numerators with Wilson intervals and the discarded-as-unknown share, Kaplan-Meier survival of directive adoption by cohort, directive lineage, declaration growth, and RFC 9728 auth-discovery conformance detail — none of it on the free surface — with an ed25519 attestation naming the chain head it was derived from. FREE SAMPLE, no credential: https://atlas.geosensor.tech/free/sample. Price $0.02 or €0.02 + 23% VAT (PT) via x402 v2 in USDC or EURC; a credential is VERIFIED and then SETTLED before anything is returned. A €19/month net + VAT subscription at https://atlas.geosensor.tech/paid/subscribe (23370000 atomic units) needs no per-call payment. TESTNET only (Base Sepolia): settlement is on-chain but moves test tokens with no monetary value. The tokens on this network are free from https://faucet.circle.com, and you need no ETH because the facilitator pays the gas.
Inputs: no named parameters.
Per-host findings. Requires a bearer credential.
Inputs: host (required).
ASK US FOR WHAT IS NOT HERE. What would you like to buy? Tell us even if it is not in this inventory. If what you need is a machine-readable convention, or a property of one across a host population, we can usually measure it for you — and if we cannot, we will say so. Call the request_capability tool with want describing what you need. Free text is fine. A contact is optional and only used to reply. Free, no credential, no payment.
Inputs: want (required), contact, would_pay.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Public AI web-readiness scanner and machine-facing observability discovery service.
Can a machine consume this page? AEO, SEO and performance scans. Page scans need no account.
Live AI visibility measurements from Are you found by AI?, queryable by your own AI.
Read-only public website inspection: evidence-backed Machine Presence observations with uncertainty.
Add one secure layer between your agents and this server.
