ssh_exec_command · SSH MCP Server MCP: Risk & Policy

WHAT IT DOES

What ssh_exec_command does on SSH MCP Server

AI agents invoke ssh_exec_command to trigger actions in SSH MCP Server. 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_exec_command needs a policy

The tool name strongly implies execution of arbitrary shell commands over SSH on remote servers. The server description explicitly states it 'enables AI assistants to execute shell commands,' and this tool is clearly the primary mechanism for that. Executing arbitrary shell commands on remote servers carries critical risk — an AI agent could run destructive, data-exfiltrating, or system-compromising commands.

From the tool's definition Tool name 'ssh_exec_command' on a server described as enabling AI assistants to 'execute shell commands and manage files on remote servers via SSH'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_exec_command Rate-limited

ssh_exec_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_exec_command": {
      "limits": [
        {
          "counter": "ssh_exec_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about ssh_exec_command

What does the ssh_exec_command tool do? +

ssh_exec_command. It is categorised as a Execute tool in the SSH MCP Server 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_exec_command? +

Register the SSH MCP Server MCP server in PolicyLayer and add a rule for ssh_exec_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 MCP Server. Nothing to install.

What risk level is ssh_exec_command? +

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

Can I rate-limit ssh_exec_command? +

Yes. Add a rate_limit block to the ssh_exec_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_exec_command completely? +

Set action: deny in the PolicyLayer policy for ssh_exec_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_exec_command? +

ssh_exec_command is provided by the SSH MCP Server MCP server (mcpol-studio/code-to-server-ssh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.