Saves the scene in a new slot
AI agents use save_new to create or update resources in Open Brush MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Open Brush MCP Server environment.
This tool creates a new save file, which is a reversible write operation. While it does not read data (Read), it creates new persistent state. It is not Destructive because existing saves remain intact and the operation is easily undone. It is not Execute because it doesn't run arbitrary code or commands.
From the tool's definition Tool description states 'Saves the scene in a new slot' — this creates a new file/save state in the Open Brush application, modifying the persistent storage without irreversibly destroying existing data.
Attacks that exploit this kind of access
Saves the scene in a new slot. It is categorised as a Write tool in the Open Brush MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Open Brush MCP Server MCP server in PolicyLayer and add a rule for save_new: 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_new is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_new 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_new. 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_new 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 →