AI agents call reset to permanently remove resources in Pane — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool resets the display to its initial state and cancels any pending input. Cancelling pending input is a one-way action that cannot be undone — any data the user had entered or any in-progress interaction is lost. This qualifies as Destructive due to the irreversible loss of pending state/input, though the blast radius is limited to the UI session rather than persistent data.
From the tool's definition 'Reset the display to initial state (cancels pending input)' — resets state and cancels pending input irreversibly
Documented attack patterns abuse exactly the kind of access reset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pane, and nothing reaches the server without passing your rules. This is the rule we recommend for reset:
{
"version": "1",
"default": "deny",
"hide": [
"reset"
]
} reset disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Reset the display to initial state (cancels pending input). It is categorised as a Destructive tool in the Pane MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pane MCP server in PolicyLayer and add a rule for reset: 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 Pane. Nothing to install.
reset 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 reset 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 reset. 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.
reset is provided by the Pane MCP server (zabaca/pane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pane, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Pane tools catalogued and risk-classified — across an index of 43,000+ MCP servers.