Leaderboard / 47620.xyz / endpoint
GET https://47620.xyz/x/mcp-trust
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 10 probes in the last 7 days.
- Category
- Web audit by llm, confidence 70%
- Latest quote
- $0.01 on Base to 0x7f4c…9d53
- 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
- 2h ago
- Next probe
- 2026-11-18 18:50 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Solana | EPjFWd…Dt1v | 5000 | 8iZbje…7j68 | default | yes | 4h ago |
| cdp | exact | Polygon | 0x3c49…3359 | 10000 | 0x7f4c…9d53 | default | yes | 4h ago |
| cdp | exact | Base | 0x8335…2913 | $0.01 | 0x7f4c…9d53 | default | yes | 4h ago |
| payai | exact | Base | 0x8335…2913 | $0.005 | 0x7f4c…9d53 | 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 |
|---|---|---|---|---|---|
| 31h ago | Web audit | 70% | llm | v1 | claude-haiku-5-5: The endpoint audits a caller-supplied URL (an MCP server) for reachability, HTTPS, advertised risky capabilities and security signals, returning a trust score and findings. That matches the web_audit category of site and security audits of a URL you supply, though the MCP-specific focus and tool-poisoning checks make it a bit closer to a security verdict than a plain header audit. |
| 41h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 2h ago | free | 402 | 310 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 8h ago | free | 402 | 299 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 15h ago | free | 402 | 305 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 21h ago | free | 402 | 670 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 27h ago | free | 402 | 644 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 34h ago | free | 402 | 1284 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 40h ago | free | 402 | 308 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 46h ago | free | 402 | 305 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 2d ago | free | 402 | 637 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |
| 2d ago | free | 402 | 634 ms | v2 | yes | $0.01 | 0x7f4c…9d53 | — |