Overview
Before an agent installs an MCP server, skill or tool: is the description poisoned (hidden orders to the agent), does it ask for more permissions than its purpose, does it imitate a known tool? Code checks (lookalike names, broad permissions, hidden text) then a reading of the descriptions. Judges the description shown, not future code behaviour. Returns allow, review or block.
Protocol
L402 (POST)
Price
25 sats
Payment Asset
—
Payment Network
—
Category
ai/agents
Provider
—
Source
self-registered
Indexed
2026-10-18 13:01:49
Health
Status
healthy
Latency (p50)
719ms
Uptime (30d)
100.0%
Reliability Score
87/100
Last Checked
2026-10-22 17:51:00
Last Healthy
2026-10-22 17:51:00
Consecutive Failures
0
Macaroon Format
Format
Not yet detected
Also available via
Recent Health Checks
| Time | Status | HTTP | Latency | Error |
|---|---|---|---|---|
| 2026-10-22 17:51:00 | healthy | 402 | 872ms | |
| 2026-10-22 04:54:30 | healthy | 402 | 470ms | |
| 2026-10-21 23:49:52 | healthy | 402 | 407ms | |
| 2026-10-21 03:38:39 | healthy | 402 | 753ms | |
| 2026-10-20 14:58:02 | healthy | 402 | 719ms | |
| 2026-10-20 09:52:46 | healthy | 402 | 517ms |