piLoci is a self-hosted MCP memory server built to save tokens, I/O, and LLM calls on low-power devices like Raspberry Pi.
- capability exposureinferred+35
- trust mitigatorsmixed−3
inferredmixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 14m ago · see ecosystem CVEs →
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit f351c9f · analyzer v17 · 2d ago
skills & prompt files 1
- agent-rulesjshsakura-oc-piloci-f351c9f/CLAUDE.md
danger signals2
- suspicious endpointapi.telegram.orgjshsakura-oc-piloci-f351c9f/src/piloci/notify/telegram.py:57
url = f"https://api.telegram.org/bot{settings.telegram_bot_token}/sendMessage" - suspicious endpointapi.telegram.orgjshsakura-oc-piloci-f351c9f/src/piloci/notify/telegram_bot.py:64
url = f"https://api.telegram.org/bot{settings.telegram_bot_token}/{method}"
[](https://mcpobservatory.com/servers/github:jshsakura/oc-piloci/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of jshsakura.