ssh_send_input · MCP SSH Server MCP: Risk & Policy

WHAT IT DOES

What ssh_send_input does on MCP SSH Server

AI agents invoke ssh_send_input to trigger actions in MCP SSH 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_send_input needs a policy

This tool sends input to an active interactive shell session on a remote server. Since it can send arbitrary commands or keystrokes to a running shell, it effectively executes operations on the remote system. The blast radius is high because an AI agent could send destructive or unauthorized commands through the interactive session, including commands to delete files, modify configurations, or compromise the system.

From the tool's definition Send input to an interactive shell session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_send_input Rate-limited

ssh_send_input 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_send_input": {
      "limits": [
        {
          "counter": "ssh_send_input_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 Server, so you can run agents against it safely.

FAQ

Questions about ssh_send_input

What does the ssh_send_input tool do? +

Send input to an interactive shell session with optional typing simulation. It is categorised as a Execute tool in the MCP SSH 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_send_input? +

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

What risk level is ssh_send_input? +

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

Can I rate-limit ssh_send_input? +

Yes. Add a rate_limit block to the ssh_send_input 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_send_input completely? +

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

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