Read a Jupyter notebook including cell outputs
AI agents call read_notebook_with_outputs to retrieve information from MCP Jupyter Complete without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves notebook contents and outputs without creating, modifying, deleting, or executing any cells. It is a pure read operation with no side effects, fitting the Read category. The severity is low because retrieving notebook data poses minimal risk; the tool cannot alter state or trigger actions.
From the tool's definition The tool name 'read_notebook_with_outputs' and description 'Read a Jupyter notebook including cell outputs' indicate a retrieval operation that queries and returns notebook data without modification or execution.
Attacks that exploit this kind of access
Read a Jupyter notebook including cell outputs. It is categorised as a Read tool in the MCP Jupyter Complete MCP Server, which means it retrieves data without modifying state.
Register the MCP Jupyter Complete MCP server in PolicyLayer and add a rule for read_notebook_with_outputs: 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 MCP Jupyter Complete. Nothing to install.
read_notebook_with_outputs 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 read_notebook_with_outputs 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 read_notebook_with_outputs. 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.
read_notebook_with_outputs is provided by the MCP Jupyter Complete MCP server (tofunori/mcp-jupyter-complete). 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 →