Methodology
How we check services, what the results mean, and what they cannot tell you.
What we publish
Only objective data: our own measurements, operators' statements paraphrased with a link to the source, and computed figures shown with their method and coverage. We do not rate, rank or recommend services.
Checks
| Check | What it does |
|---|---|
| Availability | One unpaid GET or HEAD request, without credentials, usually hourly. We record the HTTP status and the time until response headers arrive. The response body is not read. |
| Documentation, API schema | One GET request, usually daily. The body (up to 2 MB) is normalised and hashed, so a later difference is recorded as a detected change. |
A check passes when the status matches what a healthy, unpaid response looks like for that operation. For an x402 endpoint that is usually 402 Payment Required: it shows the endpoint is reachable and asking for payment. It does not show that a paid call succeeds or returns useful results.
History and freshness
- Counts cover a rolling 30-day window, or a clearly labelled shorter window when monitoring began more recently.
- Passed, failed and missed checks are reported separately. A missed check is one that was scheduled but never ran.
- A result becomes stale after two missed intervals. Stale or missing results are never shown as passing.
- Listings with under 30 days of monitoring are marked limited evidence.
- Checks run from Cloudflare data centres chosen per run; each result records its location, and response times include network distance.
Discovered services
We also read public agent registries (currently the x402 Bazaar) and probe every listed x402 service once a day with one unpaid request. A probe passes when the response is HTTP 402 carrying a valid x402 challenge (scheme, network and recipient) on a mainnet network. These entries are not reviewed by a person and are published with their evidence so agents can filter them. Registry descriptions are not republished; payer and call counts are the registry's own figures.
Trust profile
Each listing records five things an agent needs before paying or taking work: payment rails, identity, reputation, settlement and dispute resolution. Entries come from the operator's own pages, with links, using a fixed vocabulary. "Not stated" means the sources are silent.
Records and corrections
Observations are never edited or deleted. A correction is stored alongside the original, and a reworded operator statement keeps its earlier version. Anyone can report a correction from a service's page.
Contact and corrections
Email hello@agentserviceatlas.com. Security reports: security@agentserviceatlas.com (see security.txt). Corrections to a listing can also be sent from the form on its page. Every message reaches our team. Incoming mail is sorted automatically so nothing important waits, and we never publish what you send us.
Terms of use
Agents and people may query the API and use the data to make decisions, with attribution to Agent Service Atlas where results are shown to others. Bulk copying, mirroring or republishing the dataset requires permission. The service is a preview and is provided as is, without warranty.
Changelog
- 16 October 2026: monitoring and catalogue launched (availability/1, content-hash/1).
- 16 October 2026: discovered services and daily x402 probes added (candidate-x402/1).
- 17 October 2026: preview status marked on all pages and API responses; terms of use published.