AI agents use create_notebook to create or update resources in Zeppelin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zeppelin environment.
This tool creates a new notebook artifact within Zeppelin. While the description is incomplete (cuts off mid-sentence at 'Path uses'), the verb 'create' and explicit mention of notebook creation unambiguously place it in the Write category. Severity is medium: creating a notebook is reversible and has limited blast radius, though it could clutter or pollute the workspace if misused by an agent. Confidence is high (0.
From the tool's definition Tool name is 'create_notebook' and description states 'Create a new notebook' — a clear data creation action.
Attacks that exploit this kind of access
Create a new notebook at the given path. Path uses. It is categorised as a Write tool in the Zeppelin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zeppelin MCP server in PolicyLayer and add a rule for create_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 Zeppelin. Nothing to install.
create_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 create_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 create_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.
create_notebook is provided by the Zeppelin MCP server (mihneamanolache/zeppelin-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 →