remote_ssh_exec · Infra Ops MCP: Risk & Policy

WHAT IT DOES

What remote_ssh_exec does on Infra Ops

AI agents invoke remote_ssh_exec to trigger actions in Infra Ops. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why remote_ssh_exec needs a policy

This tool allows running arbitrary shell commands on remote hosts without apparent restrictions on what commands can be executed. This is classified as Execute (not Destructive) because the destructiveness depends entirely on the command passed as an argument.

From the tool's definition Tool name is "remote_ssh_exec" and description states "Execute a command on a remote host via SSH". The word "Execute" combined with remote command execution capability indicates arbitrary code execution on external systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

remote_ssh_exec Rate-limited

remote_ssh_exec stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "remote_ssh_exec": {
      "limits": [
        {
          "counter": "remote_ssh_exec_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Infra Ops, so you can run agents against it safely.

FAQ

Questions about remote_ssh_exec

What does the remote_ssh_exec tool do? +

Execute a command on a remote host via SSH. It is categorised as a Execute tool in the Infra Ops MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on remote_ssh_exec? +

Register the Infra Ops MCP server in PolicyLayer and add a rule for remote_ssh_exec: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Infra Ops. Nothing to install.

What risk level is remote_ssh_exec? +

remote_ssh_exec is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit remote_ssh_exec? +

Yes. Add a rate_limit block to the remote_ssh_exec rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block remote_ssh_exec completely? +

Set action: deny in the PolicyLayer policy for remote_ssh_exec. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides remote_ssh_exec? +

remote_ssh_exec is provided by the Infra Ops MCP server (skyvanguard/infra-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.