A sandboxed MCP server that executes shell commands inside ephemeral, locked-down Docker containers with no network by default, dropped capabilities, and an audit log, enabling secure agent-driven command execution.
An MCP server exposing narrowly scoped storage workflows with Overseer approval integration and redacted execution evidence, currently in fixture-only development for testing via stdio.
An MCP server that provides a secure, sandboxed tool execution fabric for AI agents, featuring JSON-RPC 2.0 protocol support, read-only constraints, and an observability inspector dashboard.