start_notebook · Jlab MCP: Risk & Policy

WHAT IT DOES

What start_notebook does on Jlab

AI agents invoke start_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_notebook needs a policy

Starting a notebook on a GPU cluster initiates a powerful execution environment where subsequent operations (via sibling execute_code, run_cell tools) can run arbitrary computational workloads. The ability to launch such a session is itself an Execute action—it triggers external operations (SLURM job submission, JupyterLab initialization) whose effects depend on how the agent uses the resulting session.

From the tool's definition Tool starts a notebook on a GPU-accelerated HPC environment via SLURM, enabling arbitrary Python code execution on remote compute resources. Context confirms sibling tools include 'execute_code' and 'execute_scratch' for running Python.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_notebook Rate-limited

start_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_notebook": {
      "limits": [
        {
          "counter": "start_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_notebook

What does the start_notebook tool do? +

start_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_notebook? +

Register the Jlab MCP server in PolicyLayer and add a rule for start_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_notebook? +

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

Can I rate-limit start_notebook? +

Yes. Add a rate_limit block to the start_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_notebook completely? +

Set action: deny in the PolicyLayer policy for start_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_notebook? +

start_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.