Read a notebook and return its full structure: all cells with their IDs,
AI agents call notebook_get to retrieve information from JupyterMCP 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 structure (cells, IDs) without creating, modifying, deleting, or executing anything. It has no side effects on the notebook or kernel state. This is a pure read operation with minimal blast radius if misused by an agent—it can only expose notebook contents.
From the tool's definition Tool name 'notebook_get' and description 'Read a notebook and return its full structure' clearly indicate data retrieval with no modification. The verb 'Read' is explicitly stated.
Attacks that exploit this kind of access
Read a notebook and return its full structure: all cells with their IDs,. It is categorised as a Read tool in the JupyterMCP MCP Server, which means it retrieves data without modifying state.
Register the Jupyter MCP server in PolicyLayer and add a rule for notebook_get: 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_get 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 notebook_get 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_get. 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_get 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 →