AI agents call list_notebooks to retrieve information from Zeppelin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries notebook metadata from Zeppelin without creating, modifying, deleting, or executing any operations. The query parameter enables filtering but still only returns data. The primary risk is information disclosure (what notebooks exist), which is low severity since it merely exposes organizational structure with no capability to alter state or execute code.
From the tool's definition Tool name 'list_notebooks' and description 'List notebooks in Zeppelin' with filtering capability. No modification, deletion, or execution occurs.
Attacks that exploit this kind of access
List notebooks in Zeppelin. Use the query parameter to filter by path (case-insensitive substring match). Without a query, returns all notebooks (can be very large). It is categorised as a Read tool in the Zeppelin MCP Server, which means it retrieves data without modifying state.
Register the Zeppelin MCP server in PolicyLayer and add a rule for list_notebooks: 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.
list_notebooks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_notebooks 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 list_notebooks. 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.
list_notebooks 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 →