Paywary

Leaderboard / mcp-x402.onrender.com / endpoint

POST https://mcp-x402.onrender.com/gate/calibration-court/api/v1/recalibrate

Scores measure reliability and honesty, not output quality.

75Payconfidence: medium
  • The quoted payment wallet does not match the catalog listing.
  • Quoted a price different from the listed price on 6 of 9 comparable probes.
Category
Signal by llm, confidence 55%
Latest quote
$0.001 on Base to 0x5bbd…28b2
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
1h ago
Next probe
2026-11-18 12:38 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
67w 15%
Delivery after payment
n/aexcluded
Wallet stability
0w 10%
Listing age
7w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.010xc291…dc46defaultyes3h ago

Paid probes

No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.

Delivery checks

Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.

No delivery checks yet. They run inside the weekly paid probe.

Classification history

Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.

WhenCategoryConfidenceMethodVersionEvidence
17h agoSignal55%llmv1claude-haiku-5-5: Endpoint takes a model's raw probability and returns a calibrated probability, which is a forecast-style output for prediction quality. The description is truncated and no service name or tags are given, so the fit to signal is moderate rather than certain; it could also be read as compute_math.
34h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
1h agofree402106 msv2yes$0.0010x5bbd…28b2price_below_listingprice_mismatchpayto_mismatch
7h agofree40257 msv2yes$0.0010x5bbd…28b2price_below_listingprice_mismatchpayto_mismatch
14h agofree40262 msv2yes$0.0010x5bbd…28b2price_below_listingprice_mismatchpayto_mismatch
20h agofree40246 msv2yes$0.0010x5bbd…28b2price_below_listingprice_mismatchpayto_mismatch
26h agofree402100 msv2yes$0.0010x5bbd…28b2price_below_listingprice_mismatchpayto_mismatch
32h agofree40262 msv2yes$0.0010x5bbd…28b2price_below_listingprice_mismatchpayto_mismatchprice_changed
39h agofree40243 msv2yes$0.010x5bbd…28b2payto_mismatch
45h agofree40296 msv2yes$0.010x5bbd…28b2payto_mismatch
2d agofree40242 msv2yes$0.010x5bbd…28b2payto_mismatch