Aegis — AI Agent Governance
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Open the source (opens github.com) https://github.com/acacian/aegis
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.Acacian.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
agent-aegis@0.1.6
From the server's entry in the official MCP Registry
Settings it asks for
AEGIS_POLICY_PATH· Path to YAML policy file
Related
-
aegis-mcp
MCP serversRuntime governance enforcement for AI agents. Zero token overhead.
aegis-mcp-server@0.1.15 -
aegis
MCP serversLocal stdio MCP server for the AEGIS governance client. The hosted evaluation service is offline.
aegis-governance@1.4.2 -
Aegis Policy
MCP serversGovernance firewall and safety guardrails oracle for AI swarms.
-
Execute aegis-policy-mcp
MCP serversPremium agentic endpoint for aegis-policy-mcp.
-
aegis-protocol
MCP serversTrustless escrow for AI agent-to-agent transactions on Base L2 with ERC-8004 identity and USDC.
@aegis-protocol/mcp-server@0.1.3 -
aegis
MCP serversCredential isolation for AI agents. Inject secrets at the network boundary.
@getaegis/cli@1.0.5