Rollback last transaction
AI agents call rollback_last_patch to permanently remove resources in RPG Maker MV Content Bridge — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Rolling back a transaction permanently undoes committed changes. While 'rollback' could sound reversible, in a file-based system it overwrites or discards previously applied data (the patch) irreversibly. The prior state that was patched is lost, making this a destructive operation. High severity because it can silently undo legitimate project changes made by prior tool calls.
From the tool's definition rollback_last_patch / 'Rollback last transaction' — reverses and discards the most recently applied patch/transaction
Attacks that exploit this kind of access
Rollback last transaction. It is categorised as a Destructive tool in the RPG Maker MV Content Bridge MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RPG Maker MV Content Bridge MCP server in PolicyLayer and add a rule for rollback_last_patch: 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 RPG Maker MV Content Bridge. Nothing to install.
rollback_last_patch 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 rollback_last_patch 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 rollback_last_patch. 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.
rollback_last_patch is provided by the RPG Maker MV Content Bridge MCP server (zdoss/herolink). 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 →