add_mirror_modifier
AI agents use add_mirror_modifier to create or update resources in BlenderMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BlenderMCP environment.
Adding a mirror modifier creates or modifies object properties reversibly—the modifier can be removed or adjusted without permanently destroying data. This is a Write operation (creates/modifies state) rather than Execute (which would involve running arbitrary scripts) or Destructive (which would be permanent deletion). The empty description lowers confidence slightly, but the tool name and context are clear.
From the tool's definition Tool name 'add_mirror_modifier' indicates adding a modifier to a 3D model in Blender. The server description mentions 'manipulate objects' and the sibling tools (add_decimate_modifier, add_laplacian_smooth_modifier, etc.) all perform non-destructive,…
Attacks that exploit this kind of access
add_mirror_modifier. It is categorised as a Write tool in the BlenderMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Blender MCP server in PolicyLayer and add a rule for add_mirror_modifier: 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 BlenderMCP. Nothing to install.
add_mirror_modifier 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 add_mirror_modifier 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 add_mirror_modifier. 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.
add_mirror_modifier is provided by the Blender MCP server (shirshovdim/retopoflow_blender_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 →