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.
lolxl/safespace-mcp is an MCP server distributed on github, maintained by lolxl, tracked here since June 2026. It has shipped 5 releases. Its composite risk grade is C — an inferred review prompt computed from observed signals, not a verdict.
Reading the source raised one review prompt — dangerous code — each a pattern worth a human look rather than a finding of fault.
full security breakdown →No tools recorded for this server yet.
06-20 00:00 08-03 00:00 now
| version | date | src |
|---|---|---|
| v1.127.0 | 2026-07-29 | github |
| v1.126.0 | 2026-07-15 | github |
| v1.115.3 | 2026-07-12 | github |
| v1.110.0 | 2026-06-17 | github |
| v1.80.0 | 2026-06-11 | github |