Is Nefesh — Real-Time Human State Awareness for AI MCP safe to give an agent?
A factual risk summary built from Nefesh — Real-Time Human State Awareness for AI’s real tool surface, execution model, and verification history — not a vibe. Trust score 62/100.
Has tools that can delete or irreversibly change data.
Runs on the vendor's infrastructure; you connect over the network. No untrusted code runs on your machine, but you grant the hosted service access.
Connects to a remote URL — no local package execution.
This server has write and destructive tools. No auth scopes are recorded for how that access is granted.
Worried about handing an agent raw access? See governed agents in action — Apex gives your AI paced, capped, fully-logged hands with approval queues before anything runs.
Explore Apex →See also: full server page · setup · alternatives