tool permissions — The rules governing which tools an agent may call and which need confirmation — the boundary between a mistake and an incident.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Most AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → permission models copy the single-user assistant pattern and break in collaborative environments; this lays out a deny-by-default, resource-scoped alternative that keeps safety in the access-control layer instead of the prompt.
