Select all triangle faces (3 vertices) in the mesh.
AI agents invoke select_triangles 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.
This tool executes a selection action within Blender, changing the editor's internal selection state. While it doesn't modify geometry or data permanently, it is an interactive operation within a running application (Execute), not a pure read/query of data. The blast radius is low since it only affects which faces are selected, with no destructive or financial impact.
From the tool's definition 'Select all triangle faces (3 vertices) in the mesh' — triggers a selection operation within the Blender environment, modifying the active selection state
Attacks that exploit this kind of access
Select all triangle faces (3 vertices) in the mesh. 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 select_triangles: 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.
select_triangles 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 select_triangles 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 select_triangles. 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.
select_triangles 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 →