interrupt_command · Ai Mcp Terminal MCP: Risk & Policy

WHAT IT DOES

What interrupt_command does on Ai Mcp Terminal

AI agents invoke interrupt_command to trigger actions in Ai Mcp Terminal. 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_command needs a policy

This tool sends an interrupt signal (SIGINT equivalent) to a running process in a terminal session. It actively affects execution state by stopping a running command, which qualifies as an Execute-category action. While it doesn't delete data or move money, it can terminate running processes with potentially significant side effects (e.g., interrupting a build, stopping a server, or halting a critical script).

From the tool's definition Interrupt current command but keep terminal (like Ctrl+C). Terminal becomes idle state, can continue executing new commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

interrupt_command Rate-limited

interrupt_command 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_command": {
      "limits": [
        {
          "counter": "interrupt_command_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 Ai Mcp Terminal, so you can run agents against it safely.

FAQ

Questions about interrupt_command

What does the interrupt_command tool do? +

v2.0.3: Interrupt current command but keep terminal (like Ctrl+C). Terminal becomes idle state, can continue executing new commands. Recommended: Use when need to stop command but keep terminal. It is categorised as a Execute tool in the Ai Mcp Terminal 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_command? +

Register the Ai Mcp Terminal MCP server in PolicyLayer and add a rule for interrupt_command: 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 Ai Mcp Terminal. Nothing to install.

What risk level is interrupt_command? +

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

Can I rate-limit interrupt_command? +

Yes. Add a rate_limit block to the interrupt_command 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_command completely? +

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

interrupt_command is provided by the Ai Mcp Terminal MCP server (kanniganfan/ai-mcp-terminal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.