Overview
Tool results (MCP servers, APIs, search, file reads) are untrusted content the agent re-reads. Detects a result that gives orders to the agent, strays from what the tool should return or asks to send data (tool poisoning). Returns allow, review or block.
Protocol
L402 (POST)
Price
15 sats
Payment Asset
—
Payment Network
—
Category
ai/agents
Provider
—
Source
self-registered
Indexed
2026-10-18 11:52:06
Health
Status
healthy
Latency (p50)
712ms
Uptime (30d)
100.0%
Reliability Score
90/100
Last Checked
2026-10-25 13:40:47
Last Healthy
2026-10-25 13:40:47
Consecutive Failures
0
Macaroon Format
Format
Not yet detected
Also available via
Recent Health Checks
| Time | Status | HTTP | Latency | Error |
|---|---|---|---|---|
| 2026-10-25 13:40:46 | healthy | 402 | 457ms | |
| 2026-10-24 17:15:10 | healthy | 402 | 712ms | |
| 2026-10-24 06:45:35 | healthy | 402 | 940ms | |
| 2026-10-23 14:10:12 | healthy | 402 | 739ms | |
| 2026-10-22 18:13:01 | healthy | 402 | 679ms |