Create a new Jupyter notebook (.ipynb) in the working directory.
AI agents use notebook_create 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.
This tool creates a new file (reversible write operation). While file creation is not destructive and has limited blast radius compared to Execute or Destructive actions, it modifies the file system state. Severity is medium because an agent could create many notebooks or occupy disk space, but the action is reversible via deletion.
From the tool's definition Tool name 'notebook_create' and description 'Create a new Jupyter notebook (.ipynb) in the working directory' clearly indicate file creation.
Attacks that exploit this kind of access
Create a new Jupyter notebook (.ipynb) in the working directory. 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.
Register the Jupyter MCP server in PolicyLayer and add a rule for notebook_create: 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.
notebook_create 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 notebook_create 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 notebook_create. 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.
notebook_create 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.
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 →