interrupt · Ssh MCP: Risk & Policy

WHAT IT DOES

What interrupt does on Ssh

AI agents invoke interrupt to trigger actions in 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 interrupt needs a policy

Sending Ctrl+C sends an interrupt signal (SIGINT) to the active process in the SSH session, terminating or interrupting whatever is currently running. This is an execution-side-effect operation — it actively interferes with running processes.

From the tool's definition Send Ctrl+C to the session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

interrupt Rate-limited

interrupt 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": {
    "interrupt": {
      "limits": [
        {
          "counter": "interrupt_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, so you can run agents against it safely.

FAQ

Questions about interrupt

What does the interrupt tool do? +

Send Ctrl+C to the session. It is categorised as a Execute tool in the 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 interrupt? +

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

What risk level is interrupt? +

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

Can I rate-limit interrupt? +

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

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

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