ssh_execute · Claude Ssh MCP: Risk & Policy

WHAT IT DOES

What ssh_execute does on Claude Ssh

AI agents invoke ssh_execute to trigger actions in Claude Ssh. 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_execute needs a policy

This tool runs arbitrary shell commands on remote servers via SSH. Command execution is inherently Execute-category because outcomes depend entirely on the arguments provided—an AI agent could run destructive commands (rm -rf /), read sensitive data, modify files, or trigger external operations.

From the tool's definition Tool name 'ssh_execute' and description 'Execute a command on a connected remote server' directly indicate arbitrary command execution on remote systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_execute Rate-limited

ssh_execute 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_execute": {
      "limits": [
        {
          "counter": "ssh_execute_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 Claude Ssh, so you can run agents against it safely.

FAQ

Questions about ssh_execute

What does the ssh_execute tool do? +

Execute a command on a connected remote server. It is categorised as a Execute tool in the Claude Ssh 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_execute? +

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

What risk level is ssh_execute? +

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

Can I rate-limit ssh_execute? +

Yes. Add a rate_limit block to the ssh_execute 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_execute completely? +

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

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