@agentwares/agentguard
MITMCP policy proxy for AI agents: hard spend limits, destructive-action gating with approvals, a kill switch, scoped credentials, dry-run writes with mutation diffs, loop breaker, blast-radius caps and a hash-chained audit log. No LLM calls, no phone-home,
100
Security score
0 known advisories in v0.1.5
Weekly downloads
—
Unpacked size
1.5 MB
Dependencies
4
Last publish
7 days ago
Security advisories
No known vulnerabilities affect v0.1.5.