The AI safety gateway for an agent's external surface — a provider-agnostic safety envelope (input sanitize + untrusted-content tagging, tier/scope/burst/recipient egress gates, autonomy hardening, run_id forensics, tokens behind a SecretBackend, full audit trail) between an AI agent and any source it touches. MIT.
Nothing links lolxl/safespace-mcp to another tracked server.
This view only maps edges between servers in the catalogue — a dependency on a general npm or PyPI library is not one of them. Nothing depends on this server here either.