Agent-Aegis is a governance layer for AI agents that unifies various governance primitives across multiple frameworks without requiring code changes. It provides a single API for prompt-injection blocking, PII masking, policy enforcement, and audit capabilities.
From the registry: Credential isolation for AI agents. Inject secrets at the network boundary.

$ pip install 'agent-aegis[mcp]'https://pypi.org/project/agent-aegis/Please install the `aegis` MCP server into my current AI client (that's you).
Optional prerequisites:
- Install agent-aegis — Install the Python package with MCP extras (or use uvx which installs on demand) Run: `pip install 'agent-aegis[mcp]'` (https://pypi.org/project/agent-aegis/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","agent-aegis[mcp]","aegis-mcp-proxy","--wrap","npx","-y","@modelcontextprotocol/server-filesystem","<path-to-wrap>"]
Note: Aegis is an MCP proxy that wraps another MCP server to add governance (injection/PII guardrails, audit). Replace the wrapped command/args with the target MCP server you want governed.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Smart MCP proxy with BM25 tool discovery, quarantine security, and ~99% token savings