The aegis-mcp-server is an MCP server that validates agent actions against governance policies before execution, ensuring compliance and accountability at runtime.
From the registry: Runtime governance enforcement for AI agents. Zero token overhead.

Please install the `aegis-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js 18+** — Required for npx to run the aegis-mcp-server package. (https://nodejs.org)
Optional prerequisites:
- Generate an .agentpolicy/ via aegis-cli (optional) — Use aegis-cli to scaffold governance policies in your project root before starting the server. (https://github.com/cleburn/aegis-cli)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","aegis-mcp-server","--project","."]
Note: Enforces `.agentpolicy/` files against agent actions. Add `--role <name>` to lock to a specific role; omit for universal mode where the agent picks a role at runtime.
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.Dead code, security, secrets detection and code quality for Python, TypeScript, Go.