ssh_start_interactive · Ssh Agent MCP: Risk & Policy

WHAT IT DOES

What ssh_start_interactive does on Ssh Agent

AI agents invoke ssh_start_interactive to trigger actions in Ssh Agent. 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_start_interactive needs a policy

This tool enables execution of arbitrary shell commands and scripts on remote systems via SSH, including privileged operations (sudo). While not irreversibly destructive by itself, it can be used to run any command including destructive operations. The interactive nature and explicit mention of sudo elevation makes this an Execute risk rather than Write or Read.

From the tool's definition Tool description indicates it 'starts interactive SSH session' and explicitly supports 'sudo, vim, mysql and other commands requiring interactive input'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_start_interactive Rate-limited

ssh_start_interactive 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_start_interactive": {
      "limits": [
        {
          "counter": "ssh_start_interactive_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 Agent, so you can run agents against it safely.

FAQ

Questions about ssh_start_interactive

What does the ssh_start_interactive tool do? +

启动交互式SSH会话（支持sudo、vim、mysql等需要交互输入的命令）. It is categorised as a Execute tool in the Ssh Agent 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_start_interactive? +

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

What risk level is ssh_start_interactive? +

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

Can I rate-limit ssh_start_interactive? +

Yes. Add a rate_limit block to the ssh_start_interactive 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_start_interactive completely? +

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

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