Acacian/aegis
github Python analyzed 134580e
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
Acacian/aegis is an MCP server distributed on github, maintained by Acacian, tracked here since June 2026. It has shipped 19 releases and exposes 5 tools. Tools include check_risk, evaluate_action, evaluate_batch, get_policy, update_policy. Its composite risk grade is B — an inferred review prompt computed from observed signals, not a verdict.
what we found
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 →tools
-
check_risk -
evaluate_action -
evaluate_batch -
get_policy -
update_policy
release cadence · 90d
2026-07-21 2026-09-03 now
recent releases
| version | date | src |
|---|---|---|
| v1.0.0 | 2026-08-08 | github |
| v0.9.5 | 2026-04-27 | github |
| v0.9.4 | 2026-04-11 | github |
| v0.9.3 | 2026-04-06 | github |
| v0.9.2 | 2026-04-06 | github |
| v0.9.1 | 2026-04-05 | github |
| v0.7.0 | 2026-04-02 | github |
| v0.6.1 | 2026-03-29 | github |
| v0.6.0 | 2026-03-27 | github |
| v0.5.0 | 2026-03-25 | github |