Give AI agents safe, limited SSH access without handing them a shell.
Aegis-SSH-MCP is a small MCP-native bridge that lets an AI agent run approved commands on Linux hosts over SSH.
It is built for people who want agentic infrastructure workflows, but do not want to give an AI unrestricted terminal access.
MCP-native SSH bridge for AI agents with host-scoped access, rule-based command validation, ephemeral SSH sessions, and audit logging
Estrelas
4
Ferramentas
—
Disponibilidade
—
Aegis sits between your MCP client and your servers. It checks every requested command against your rules, opens a short-lived SSH session only when the command is allowed, returns the result, and disconnects.
Aegis does not replace SSH, Linux permissions, sudo, or host hardening. It helps you keep those controls in charge while giving MCP clients a safer way to interact with real systems.
AI agents are useful when they can inspect logs, check services, look at containers, or run routine operational commands.
The dangerous version of that is simple:
Give the agent SSH access and hope it behaves.
Aegis takes a safer approach:
Give the agent a narrow MCP tool that can only run commands you have approved.
That means an agent can do things like check Docker status, read logs, or run diagnostics without receiving a persistent shell, a pseudo-terminal, SSH agent forwarding, or hidden session state.
Good fit
Aegis is useful when you want to:
connect an MCP client to Linux hosts over SSH
let agents run a small set of operational commands
keep command access host-scoped and rule-based
audit what the agent tried to do
preserve your existing SSH, Linux, sudo, and host security model
What Aegis is not
Aegis is intentionally narrow.
It is not a replacement for SSH, Linux permissions, sudo, IAM, RBAC, host hardening, or human judgment.
It does not:
give agents a persistent shell
create hidden session state
provide full OS-level sandboxing
approve commands through a human workflow
turn MCP into a full infrastructure automation platform
That is by design.
Aegis does one job:
It gives an MCP client a controlled, auditable way to run approved SSH commands -- and leaves the rest of your security model intact.
Quick start
The recommended way to run Aegis is with the included docker-compose.yml.
Prerequisites:
Docker Compose
an MCP client with SSE support
a reachable Linux host
an SSH key or password for a least-privileged remote user
By default, Aegis exposes MCP over SSE at:
http://localhost:8443
Starter rule profiles are included in rules/. Keep or copy those profiles when deploying; the quick start only requires you to add host configs and SSH credentials.
1. Create the local folders
Create these folders next to docker-compose.yml if they do not already exist:
./configs
./keys
./certs # only needed if you enable HTTPS
The repository already includes ./rules with starter rule profiles.
2. Add an SSH key
Place the SSH private key Aegis should use in keys/.
Keep the key permissions strict and use a dedicated, least-privileged SSH user where possible.
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Perguntas
Como instalo Aegis SSH?
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Aegis SSH precisa de uma chave de API?
Este registro não lista nenhuma variável de ambiente obrigatória.
Qual transporte Aegis SSH usa?
Aegis SSH roda localmente via stdio.
Quando Aegis SSH foi verificado pela última vez?
Última verificação: 2026-10-28. MCP-native SSH bridge for AI agents with host-scoped access, rule-based command validation, ephemeral SSH sessions, and audit logging