cell_add · Jupyter MCP: Risk & Policy

WHAT IT DOES

What cell_add does on JupyterMCP

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

WHY IT NEEDS A POLICY

Why cell_add needs a policy

The tool creates new notebook cells, which is a write operation that modifies notebook structure reversibly. While the description is empty, context from the server description and sibling tools confirms this is a cell creation function. Severity is medium because added cells could introduce unwanted code or configuration, but the operation is reversible (unlike destructive operations).

From the tool's definition Tool is named 'cell_add' and belongs to a server that 'enables AI agents to create, read, edit, and execute Jupyter notebook cells'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cell_add Rate-limited

cell_add 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": {
    "cell_add": {
      "limits": [
        {
          "counter": "cell_add_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 JupyterMCP, so you can run agents against it safely.

FAQ

Questions about cell_add

What does the cell_add tool do? +

cell_add. It is categorised as a Write tool in the JupyterMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cell_add? +

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

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

Can I rate-limit cell_add? +

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

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

cell_add 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.