kernel_start · Jupyter MCP: Risk & Policy

WHAT IT DOES

What kernel_start does on JupyterMCP

AI agents invoke kernel_start 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_start needs a policy

kernel_start triggers external operations (Jupyter kernel initialization) whose effects depend on arguments and context. This enables arbitrary code execution through subsequent cell_execute calls. While kernel startup alone is not immediately destructive, it is a critical precursor to Execute operations and represents the ability to trigger computational processes.

From the tool's definition Tool 'kernel_start' with context from sibling tools (cell_execute, kernel_interrupt, kernel_restart) on a Jupyter server that 'enables AI agents to create, read, edit, and execute Jupyter notebook cells.' Starting a kernel initiates code execution environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kernel_start Rate-limited

kernel_start 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_start": {
      "limits": [
        {
          "counter": "kernel_start_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_start

What does the kernel_start tool do? +

kernel_start. 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_start? +

Register the Jupyter MCP server in PolicyLayer and add a rule for kernel_start: 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_start? +

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

Can I rate-limit kernel_start? +

Yes. Add a rate_limit block to the kernel_start 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_start completely? +

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

kernel_start 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.