start_new_notebook · Jlab MCP: Risk & Policy

WHAT IT DOES

What start_new_notebook does on Jlab

AI agents invoke start_new_notebook 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 start_new_notebook needs a policy

This tool triggers external operations (kernel startup, session initialization on remote HPC infrastructure) whose effects depend on subsequent arguments and usage. While it doesn't directly execute code itself, it establishes the execution context for arbitrary computations on privileged GPU resources within a SLURM cluster.

From the tool's definition Tool 'start_new_notebook' initiates a new kernel and notebook session on GPU-accelerated SLURM-managed HPC resources. The description indicates it 'start[s] kernel, create[s] notebook,' which prepares a computational environment for arbitrary code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_new_notebook Rate-limited

start_new_notebook 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": {
    "start_new_notebook": {
      "limits": [
        {
          "counter": "start_new_notebook_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 start_new_notebook

What does the start_new_notebook tool do? +

Start a new session: start kernel, create notebook. 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 start_new_notebook? +

Register the Jlab MCP server in PolicyLayer and add a rule for start_new_notebook: 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 start_new_notebook? +

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

Can I rate-limit start_new_notebook? +

Yes. Add a rate_limit block to the start_new_notebook 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 start_new_notebook completely? +

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

start_new_notebook 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.