ipynb_split_notebook
AI agents use ipynb_split_notebook to create or update resources in Jupyter Editor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jupyter Editor environment.
Based on the tool name, 'ipynb_split_notebook' likely splits a Jupyter notebook into multiple notebooks, which is a write/create operation producing new files. This could also potentially modify or fragment the original notebook. Given the server context of editing notebooks and sibling tools that write/modify notebooks, Write is the most likely category.
From the tool's definition Tool name: ipynb_split_notebook; description is empty and uninformative.
Attacks that exploit this kind of access
ipynb_split_notebook. It is categorised as a Write tool in the Jupyter Editor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jupyter Editor MCP server in PolicyLayer and add a rule for ipynb_split_notebook: 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 Jupyter Editor. Nothing to install.
ipynb_split_notebook is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ipynb_split_notebook 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 ipynb_split_notebook. 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.
ipynb_split_notebook is provided by the Jupyter Editor MCP server (jsamuel1/jupyter-editor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →