run_all_cells

THE RISK

High Risk

Why run_all_cells needs a policy

This tool executes notebook cells containing arbitrary code, which can trigger external operations, modify system state, or produce side effects depending on what code is in the notebook. While it requires user approval, the potential blast radius is high given the ability to run all code in a notebook without reviewing individual cells first.

From the tool's definition Tool description states 'run all cells in the notebook' - directly executes arbitrary code within the notebook environment. The tool name and description explicitly indicate code execution.

Documented attack patterns abuse exactly the kind of access run_all_cells gives an agent:

POLICY

How to control run_all_cells

PolicyLayer is an MCP gateway — it sits between your AI agents and JupyterMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_all_cells:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_all_cells": {
      "limits": [
        {
          "counter": "run_all_cells_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_all_cells 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.

Create a free account and register JupyterMCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More JupyterMCP tools

Execute run_cell Run a specific cell by its index Args: index: The index of the cell to ru Execute edit_cell_content Edit the content of a specific cell by its index and optionally execute it Args: Execute insert_and_execute_cell Insert a cell at the specified position and execute it, and optionally set slideshow type. Write save_notebook Save the current Jupyter notebook Write set_slideshow_type set_slideshow_type Read get_cell_text_output Get the text output content of a specific code cell by its index Args: in Read get_cells_info Get information about all cells in the notebook Read get_image_output Get image outputs from a specific cell by its index Args: index: The inde

All 11 JupyterMCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in JupyterMCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_all_cells

What does the run_all_cells tool do? +

Restart and run all cells in the notebook. You need to wait for user approval. It is categorised as a Execute tool in the JupyterMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_all_cells? +

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

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

Can I rate-limit run_all_cells? +

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

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

run_all_cells is provided by the Jupyter MCP server (jjsantos01/jupyter-notebook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every JupyterMCP tool call.

Start from JupyterMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →