Insert a cell at the specified position and execute it, and optionally set slideshow type. If code cell, it will be executed. If markdown cell, it will be rendered. Args: cell_type: The type of cell ('code' or 'markdown') position: The position to insert the cell at content: The content of the ce...
AI agents invoke insert_and_execute_cell to trigger actions in JupyterMCP. 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.
This tool inserts arbitrary code into a Jupyter notebook and immediately executes it. An AI agent could inject and run any Python code, enabling full system access, data exfiltration, file deletion, network calls, or any other operation the kernel user has permissions to perform. The blast radius is critical as it provides unrestricted code execution in the notebook environment.
From the tool's definition Insert a cell at the specified position and execute it — 'If code cell, it will be executed'
Documented attack patterns abuse exactly the kind of access insert_and_execute_cell gives an agent:
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 insert_and_execute_cell:
{
"version": "1",
"default": "deny",
"tools": {
"insert_and_execute_cell": {
"limits": [
{
"counter": "insert_and_execute_cell_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}insert_and_execute_cell 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.
Free to start. No card required.
Insert a cell at the specified position and execute it, and optionally set slideshow type. If code cell, it will be executed. If markdown cell, it will be rendered. Args: cell_type: The type of cell ('code' or 'markdown') position: The position to insert the cell at content: The content of the cell slideshow_type: Optional slideshow type ('slide', 'subslide', 'fragment', 'skip', 'notes'). 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.
Register the Jupyter MCP server in PolicyLayer and add a rule for insert_and_execute_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 JupyterMCP. Nothing to install.
insert_and_execute_cell is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the insert_and_execute_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.
Set action: deny in the PolicyLayer policy for insert_and_execute_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.
insert_and_execute_cell 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.
Start from JupyterMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 JupyterMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.