Saves the scene by overwriting the last save
AI agents call save_overwrite to permanently remove resources in Open Brush MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Overwriting a save file is an irreversible operation: once the previous save is replaced, it cannot be recovered. This constitutes a destructive action as it permanently destroys the previous saved state of the scene.
From the tool's definition 'save_overwrite' and 'overwriting the last save' — this irreversibly replaces the previous save file with the current state, making the prior version unrecoverable.
Attacks that exploit this kind of access
Saves the scene by overwriting the last save. It is categorised as a Destructive tool in the Open Brush MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Open Brush MCP Server MCP server in PolicyLayer and add a rule for save_overwrite: 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 Open Brush MCP Server. Nothing to install.
save_overwrite 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 save_overwrite 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 save_overwrite. 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.
save_overwrite is provided by the Open Brush MCP Server MCP server (moz411/openbrush-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 →