interrupt_kernel · Jlab MCP: Risk & Policy

WHAT IT DOES

What interrupt_kernel does on Jlab

AI agents invoke interrupt_kernel to trigger actions in Jlab. 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_kernel needs a policy

The tool executes an action that affects a running process on a remote GPU-accelerated SLURM job. While not destructive (it doesn't delete data or cause permanent harm), it actively interrupts computation whose continuation depends on the tool's invocation. This fits Execute rather than Write because it triggers an external operation with side effects beyond simple data modification.

From the tool's definition Tool name 'interrupt_kernel' and description 'Interrupt the running kernel to stop execution' indicate it triggers an external operation (kernel interruption) on a remote HPC compute node.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

interrupt_kernel Rate-limited

interrupt_kernel 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_kernel": {
      "limits": [
        {
          "counter": "interrupt_kernel_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 Jlab, so you can run agents against it safely.

FAQ

Questions about interrupt_kernel

What does the interrupt_kernel tool do? +

Interrupt the running kernel to stop execution. It is categorised as a Execute tool in the Jlab 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_kernel? +

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

What risk level is interrupt_kernel? +

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

Can I rate-limit interrupt_kernel? +

Yes. Add a rate_limit block to the interrupt_kernel 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_kernel completely? +

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

interrupt_kernel is provided by the Jlab MCP server (kdkyum/jlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.