ssh_run_async

THE RISK

High Risk

Why ssh_run_async needs a policy

This tool executes commands on remote infrastructure via SSH. Execution of arbitrary commands on server fleets poses a high blast radius if misused by an AI agent—commands could modify system state, access sensitive data, or trigger unintended infrastructure changes.

From the tool's definition Tool name 'ssh_run_async' and description 'Start SSH command asynchronously' indicate execution of arbitrary SSH commands on remote hosts.

Documented attack patterns abuse exactly the kind of access ssh_run_async gives an agent:

POLICY

How to control ssh_run_async

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP SSH Orchestrator, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh_run_async:

policy.json

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

ssh_run_async 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.

Create a free account and register MCP SSH Orchestrator — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP SSH Orchestrator tools

Execute ssh_cancel Request cancellation for a running task. Execute ssh_cancel_async_task Cancel a running async task. Execute ssh_run Execute SSH command with policy, network checks, progress, timeout, and cancellation. Execute ssh_run_on_tag Execute SSH command on all hosts with a tag (with network checks). Execute ssh_reload_config Reload configuration files. Read ssh_describe_host Return host definition in JSON. Read ssh_get_task_output Get recent output lines from running or completed task. Read ssh_get_task_result Get final result of completed task (SEP-1686 compliant).

All 13 MCP SSH Orchestrator tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP SSH Orchestrator → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ssh_run_async

What does the ssh_run_async tool do? +

Start SSH command asynchronously (SEP-1686 compliant). It is categorised as a Execute tool in the MCP SSH Orchestrator 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_run_async? +

Register the MCP SSH Orchestrator MCP server in PolicyLayer and add a rule for ssh_run_async: 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 MCP SSH Orchestrator. Nothing to install.

What risk level is ssh_run_async? +

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

Can I rate-limit ssh_run_async? +

Yes. Add a rate_limit block to the ssh_run_async 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_run_async completely? +

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

ssh_run_async is provided by the MCP SSH Orchestrator MCP server (samerfarida/mcp-ssh-orchestrator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP SSH Orchestrator tool call.

Start from MCP SSH Orchestrator, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →