ssh_run_persistent · Mcp Ssh Live MCP: Risk & Policy

WHAT IT DOES

What ssh_run_persistent does on Mcp Ssh Live

AI agents invoke ssh_run_persistent to trigger actions in Mcp Ssh Live. 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_run_persistent needs a policy

This tool executes arbitrary code/commands on remote SSH-connected systems with persistent process handling, stdin injection, and signal control. The blast radius is critical—an agent could run destructive commands, exfiltrate data, install backdoors, or compromise remote infrastructure. While the tool description is empty, the server description and sibling tool context make the execution capability unambiguous.

From the tool's definition Tool is part of an 'Interactive, streaming SSH tool for LLM agents that enables spawning long-running remote commands with live line-by-line output, signal handling, stdin input, and SFTP file transfer.' The presence of sibling tools like 'ssh_exec',…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_run_persistent Rate-limited

ssh_run_persistent 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_run_persistent": {
      "limits": [
        {
          "counter": "ssh_run_persistent_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 Mcp Ssh Live, so you can run agents against it safely.

FAQ

Questions about ssh_run_persistent

What does the ssh_run_persistent tool do? +

ssh_run_persistent. It is categorised as a Execute tool in the Mcp Ssh Live 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_persistent? +

Register the Mcp Ssh Live MCP server in PolicyLayer and add a rule for ssh_run_persistent: 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 Live. Nothing to install.

What risk level is ssh_run_persistent? +

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

Can I rate-limit ssh_run_persistent? +

Yes. Add a rate_limit block to the ssh_run_persistent 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_persistent completely? +

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

ssh_run_persistent is provided by the Mcp Ssh Live MCP server (pmboxbiz/mcp-ssh-live). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.