smooth_vertices
AI agents invoke smooth_vertices to trigger actions in BlenderMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Based on the tool name and server context (BlenderMCP, which executes Python scripts and manipulates 3D objects in Blender), 'smooth_vertices' most likely applies a smoothing operation to mesh vertices in Blender. This is a geometry modification action executed within the Blender environment. It is reversible (Blender supports undo), so Write or Execute is more appropriate than Destructive.
From the tool's definition Tool name: 'smooth_vertices'; description is empty and uninformative.
Attacks that exploit this kind of access
smooth_vertices. It is categorised as a Execute tool in the BlenderMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Blender MCP server in PolicyLayer and add a rule for smooth_vertices: 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.
smooth_vertices is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the smooth_vertices 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 smooth_vertices. 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.
smooth_vertices 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 →