execute_ssh · SSH MCP Server MCP: Risk & Policy

WHAT IT DOES

What execute_ssh does on SSH MCP Server

AI agents invoke execute_ssh 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 execute_ssh needs a policy

This tool permits execution of arbitrary shell commands on remote Linux hosts with effects dependent entirely on the command arguments provided. Remote command execution is inherently dangerous—an AI agent could execute destructive commands (rm -rf /), exfiltrate data, modify system configurations, install malware, or pivot to other systems.

From the tool's definition Tool named 'execute_ssh' with description 'Execute command on remote Linux host via SSH' directly enables arbitrary command execution on remote systems via SSH.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_ssh Rate-limited

execute_ssh 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": {
    "execute_ssh": {
      "limits": [
        {
          "counter": "execute_ssh_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 execute_ssh

What does the execute_ssh tool do? +

Legacy compatibility - Execute command on remote Linux host via SSH. 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 execute_ssh? +

Register the SSH MCP Server MCP server in PolicyLayer and add a rule for execute_ssh: 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 execute_ssh? +

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

Can I rate-limit execute_ssh? +

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

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

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