ssh_start_async_command · Ssh Agent MCP: Risk & Policy

WHAT IT DOES

What ssh_start_async_command does on Ssh Agent

AI agents invoke ssh_start_async_command to trigger actions in Ssh Agent. 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 ssh_start_async_command needs a policy

This tool executes arbitrary commands on remote systems via SSH without waiting for completion. Async command execution on remote machines is an Execute-category action: it triggers external operations whose effects are entirely dependent on the command arguments passed. An AI agent could execute harmful commands, scripts, or administrative actions on remote systems.

From the tool's definition Tool is described as starting long-running asynchronous commands (ssh_start_async_command). The server context indicates it 'enables AI assistants to manage SSH connections, execute commands, and transfer files'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_start_async_command Rate-limited

ssh_start_async_command 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": {
    "ssh_start_async_command": {
      "limits": [
        {
          "counter": "ssh_start_async_command_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 Ssh Agent, so you can run agents against it safely.

FAQ

Questions about ssh_start_async_command

What does the ssh_start_async_command tool do? +

启动长时间运行的异步命令. It is categorised as a Execute tool in the Ssh Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ssh_start_async_command? +

Register the Ssh Agent MCP server in PolicyLayer and add a rule for ssh_start_async_command: 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 Ssh Agent. Nothing to install.

What risk level is ssh_start_async_command? +

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

Can I rate-limit ssh_start_async_command? +

Yes. Add a rate_limit block to the ssh_start_async_command 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 ssh_start_async_command completely? +

Set action: deny in the PolicyLayer policy for ssh_start_async_command. 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 ssh_start_async_command? +

ssh_start_async_command is provided by the Ssh Agent MCP server (zhijun/ssh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.