kernel_interrupt · Jupyter MCP: Risk & Policy

WHAT IT DOES

What kernel_interrupt does on JupyterMCP

AI agents invoke kernel_interrupt to trigger actions in JupyterMCP. 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 kernel_interrupt needs a policy

Sending an interrupt signal to a running kernel is an external operation that affects the execution state of the kernel. It is not purely destructive (no data is deleted), not financial, and not a simple read/write — it executes a control action against a live process. Misuse could disrupt ongoing computations but is generally recoverable, hence medium severity.

From the tool's definition 'Send an interrupt signal to the running kernel. Use this to stop a' — triggers an external kernel operation (interrupt signal)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kernel_interrupt Rate-limited

kernel_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": {
    "kernel_interrupt": {
      "limits": [
        {
          "counter": "kernel_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 JupyterMCP, so you can run agents against it safely.

FAQ

Questions about kernel_interrupt

What does the kernel_interrupt tool do? +

Send an interrupt signal to the running kernel. Use this to stop a. It is categorised as a Execute tool in the JupyterMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on kernel_interrupt? +

Register the Jupyter MCP server in PolicyLayer and add a rule for kernel_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 JupyterMCP. Nothing to install.

What risk level is kernel_interrupt? +

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

Can I rate-limit kernel_interrupt? +

Yes. Add a rate_limit block to the kernel_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 kernel_interrupt completely? +

Set action: deny in the PolicyLayer policy for kernel_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 kernel_interrupt? +

kernel_interrupt is provided by the Jupyter MCP server (try3d/jupytermcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.