select_non_manifold
AI agents invoke select_non_manifold 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, this likely selects non-manifold geometry in Blender (mesh elements with topological errors). Selection operations in Blender are typically Read/Execute level — they modify the active selection state within the 3D scene but don't irreversibly destroy data. The empty description lowers confidence.
From the tool's definition Tool name 'select_non_manifold' and server context (Blender MCP with Python script execution). Description is empty/uninformative.
Attacks that exploit this kind of access
select_non_manifold. 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_non_manifold: 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_non_manifold 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_non_manifold 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_non_manifold. 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_non_manifold 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 →