Security / Aegis — AI Agent Governance
Aegis — AI Agent Governance
io.github.Acacian/aegis · v0.1.7
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Install
uvx agent-aegisTypical command from the package name. Check the README for required configuration and credentials before connecting it to real data.
Signals
| GitHub stars | 18 |
| npm weekly downloads | - |
| Last push | 2mo ago |
| Licence | MIT |
| Open issues | 4 |
| SECURITY.md | Yes |
| Language | Python |
| Latest version published | 2026-03-22 |
Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.
Similar servers
mcpcut
Score 78Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval
prompt-protection
Score 85Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
toolgovern
Score 72Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.