Acacian/aegis
MCP Security & AuthA unified governance layer for AI agents that adds prompt‑injection blocking, PII masking, policy enforcement and audit across 12 frameworks with a single API call
Features
- Provides universal primitives (Action, Policy, Guardrails) for agent tool calls
- Auto‑instrumentation supports 12 major AI‑agent frameworks without code changes
- Offers declarative policy rules, RBAC, rate limits and tamper‑evident audit logs
Recent releases
View all 18 releases →
Review required
v0.9.1
Security relevant
Auth
RBAC
Privilege escalation + resource gaming fixes
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Install & Platforms
Install via
pip
