add_cell · MCP Jupyter Complete MCP: Risk & Policy

WHAT IT DOES

What add_cell does on MCP Jupyter Complete

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

WHY IT NEEDS A POLICY

Why add_cell needs a policy

This tool creates new notebook cells, which modifies the notebook structure and content. While reversible (cells can be deleted), it alters the notebook state. It is Write rather than Execute because adding a cell itself does not run code or trigger external operations—execution would happen via separate execute_cell tool.

From the tool's definition 'Add a new cell to the notebook' - this creates new content in the notebook, modifying its structure reversibly. The tool name 'add_cell' and description clearly indicate a creation operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_cell Rate-limited

add_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_cell": {
      "limits": [
        {
          "counter": "add_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 MCP Jupyter Complete, so you can run agents against it safely.

FAQ

Questions about add_cell

What does the add_cell tool do? +

Add a new cell to the notebook. It is categorised as a Write tool in the MCP Jupyter Complete 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_cell? +

Register the MCP Jupyter Complete MCP server in PolicyLayer and add a rule for add_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 MCP Jupyter Complete. Nothing to install.

What risk level is add_cell? +

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

Can I rate-limit add_cell? +

Yes. Add a rate_limit block to the add_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_cell completely? +

Set action: deny in the PolicyLayer policy for add_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_cell? +

add_cell is provided by the MCP Jupyter Complete MCP server (tofunori/mcp-jupyter-complete). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.