kernel_restart · Jupyter MCP: Risk & Policy

WHAT IT DOES

What kernel_restart does on JupyterMCP

AI agents invoke kernel_restart 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_restart needs a policy

kernel_restart restarts a Jupyter kernel, halting current computations and reinitializing state. This is an Execute action (not Read, Write, or Destructive) because it triggers external operations—kernel process management—whose effects depend on the kernel's state and running cells. Severity is high because an agent could interrupt critical long-running analyses or cause data loss in memory without user consent.

From the tool's definition Server enables 'execute Jupyter notebook cells' and manage kernels; kernel_restart directly controls kernel lifecycle, which triggers execution environment resets with side effects on running computations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kernel_restart Rate-limited

kernel_restart 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_restart": {
      "limits": [
        {
          "counter": "kernel_restart_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_restart

What does the kernel_restart tool do? +

kernel_restart. 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_restart? +

Register the Jupyter MCP server in PolicyLayer and add a rule for kernel_restart: 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_restart? +

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

Can I rate-limit kernel_restart? +

Yes. Add a rate_limit block to the kernel_restart 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_restart completely? +

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

kernel_restart 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.