Leaderboard / verdict.kechlab.com / endpoint
POST https://verdict.kechlab.com/v1/mcp-vet
Scores measure reliability and honesty, not output quality.
- Quoted a price different from the listed price on 11 of 11 comparable probes.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Category
- Web audit by llm, confidence 35%
- Latest quote
- $0.0167 on Base to 0xb36c…54Eb
- 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
- 28m ago
- Next probe
- 2026-11-19 01:37 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.0214 | 0xb36c…54Eb | default | yes | 3h 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.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 37h ago | Web audit | 35% | llm | v1 | claude-haiku-5-5: The endpoint vets MCP server, skill, or tool descriptions for poisoning, excessive permissions, and lookalike names before installation. That is a security audit of supplied software artifacts, closest to web_audit, though it is not a website audit and none of the listed categories fits exactly. Confidence is moderate because the description is truncated and the target is not a URL. |
| 46h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 28m ago | free | 402 | 768 ms | v2 | yes | $0.0167 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 8h ago | free | 402 | 845 ms | v2 | yes | $0.0171 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 14h ago | free | 402 | 1218 ms | v2 | yes | $0.0172 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 20h ago | free | 402 | 468 ms | v2 | yes | $0.0173 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 27h ago | free | 402 | 586 ms | v2 | yes | $0.017 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 33h ago | free | 402 | 819 ms | v2 | yes | $0.0171 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 40h ago | free | 402 | 580 ms | v2 | yes | $0.0173 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 46h ago | free | 402 | 465 ms | v2 | yes | $0.0174 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 2d ago | free | 402 | 473 ms | v2 | yes | $0.0171 | 0xb36c…54Eb | price_below_listingprice_mismatch |
| 2d ago | free | 402 | 566 ms | v2 | yes | $0.0171 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 3d ago | free | 402 | 608 ms | v2 | yes | $0.0173 | 0xb36c…54Eb | price_below_listingprice_mismatch |