sshExecute · Infer MCP Server MCP: Risk & Policy

WHAT IT DOES

What sshExecute does on Infer MCP Server

AI agents invoke sshExecute to trigger actions in Infer 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 sshExecute needs a policy

This tool runs commands on external systems with effects determined entirely by the command argument supplied by the AI agent. The blast radius is critical—an agent could execute destructive, financial, or reconnaissance commands depending on the remote server's permissions and purpose.

From the tool's definition Tool name "sshExecute" and description "Execute a command on a remote server via SSH using a configured profile" explicitly indicates execution of arbitrary commands on remote infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sshExecute Rate-limited

sshExecute 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": {
    "sshExecute": {
      "limits": [
        {
          "counter": "sshexecute_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 Infer MCP Server, so you can run agents against it safely.

FAQ

Questions about sshExecute

What does the sshExecute tool do? +

Execute a command on a remote server via SSH using a configured profile. It is categorised as a Execute tool in the Infer 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 sshExecute? +

Register the Infer MCP Server MCP server in PolicyLayer and add a rule for sshExecute: 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 Infer MCP Server. Nothing to install.

What risk level is sshExecute? +

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

Can I rate-limit sshExecute? +

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

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

sshExecute is provided by the Infer MCP Server MCP server (jackyxhb/infermcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.