add_notebook_cell · ML Jupyter MCP: Risk & Policy

WHAT IT DOES

What add_notebook_cell does on ML Jupyter MCP

AI agents use add_notebook_cell to create or update resources in ML Jupyter MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ML Jupyter MCP environment.

WHY IT NEEDS A POLICY

Why add_notebook_cell needs a policy

The tool's primary described action is adding a cell to a notebook, which is a Write operation. However, the optional execution capability elevates the risk significantly — if the cell is executed, arbitrary Python code runs in a persistent kernel context, making misuse potentially severe.

From the tool's definition 'Add a cell to a Jupyter notebook and optionally execute it' — primary action is adding/modifying a notebook (Write), but the 'optionally execute it' clause introduces Execute-level risk

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_notebook_cell Rate-limited

add_notebook_cell stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_notebook_cell": {
      "limits": [
        {
          "counter": "add_notebook_cell_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ML Jupyter MCP, so you can run agents against it safely.

FAQ

Questions about add_notebook_cell

What does the add_notebook_cell tool do? +

Add a cell to a Jupyter notebook and optionally execute it. It is categorised as a Write tool in the ML Jupyter MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_notebook_cell? +

Register the ML Jupyter MCP server in PolicyLayer and add a rule for add_notebook_cell: 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 ML Jupyter MCP. Nothing to install.

What risk level is add_notebook_cell? +

add_notebook_cell is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_notebook_cell? +

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

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

add_notebook_cell is provided by the ML Jupyter MCP server (mayank-ketkar-sf/claudejupy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.