Take screenshot of generated component for verification
AI agents call verify_component_visual to retrieve information from MCP-Blender without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is a passive observation operation that retrieves visual information about the current state of a component. It does not create, modify, delete, execute scripts, or commit financial transactions. While it occurs within Blender, the tool itself performs no destructive or risky operations—it simply documents the visual output of prior modeling operations for human review.
From the tool's definition Tool takes a screenshot for verification purposes—a read-only operation that captures visual state without modifying Blender data, executing arbitrary code, or triggering external side effects.
Attacks that exploit this kind of access
Take screenshot of generated component for verification. It is categorised as a Read tool in the MCP-Blender MCP Server, which means it retrieves data without modifying state.
Register the MCP-Blender MCP server in PolicyLayer and add a rule for verify_component_visual: 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 MCP-Blender. Nothing to install.
verify_component_visual is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the verify_component_visual 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 verify_component_visual. 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.
verify_component_visual is provided by the MCP-Blender MCP server (shdann/mcp-blend). 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 →