Clear all outputs from code cells in one or more Jupyter Notebooks (.ipynb).
AI agents call ipynb_clear_outputs to permanently remove resources in Jupyter Editor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing all outputs from notebook cells is an irreversible destructive action — once outputs are wiped, the previously computed results (which may have taken significant time/resources to generate) are permanently lost unless the user re-runs the notebook. The tool can affect multiple notebooks at once ('one or more'), amplifying the blast radius.
From the tool's definition Clear all outputs from code cells in one or more Jupyter Notebooks
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Clear all outputs from code cells in one or more Jupyter Notebooks (.ipynb). It is categorised as a Destructive tool in the Jupyter Editor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Jupyter Editor MCP server in PolicyLayer and add a rule for ipynb_clear_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 Jupyter Editor. Nothing to install.
ipynb_clear_outputs is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the ipynb_clear_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 ipynb_clear_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.
ipynb_clear_outputs is provided by the Jupyter Editor MCP server (jsamuel1/jupyter-editor-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 →