get_viewport_screenshot

What get_viewport_screenshot does on BlenderMCP

AI agents call get_viewport_screenshot to retrieve information from BlenderMCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why get_viewport_screenshot is rated Low

The tool retrieves a visual representation of the current state of the Blender viewport. It performs no side effects, creates no new objects, executes no code, and does not modify the scene or persists any data. This is purely a read operation analogous to a query or fetch. Even in a misuse scenario, the worst outcome would be information disclosure of what is currently on screen, making it low severity.

From the tool's definition Tool name is 'get_viewport_screenshot' and description states 'Capture a screenshot of the current viewport' — this is a retrieval operation that captures visual data without modifying, deleting, or executing operations in Blender.

The rule that runs get_viewport_screenshot safely

PolicyLayer is an MCP gateway: it sits between your AI agents and BlenderMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_viewport_screenshot, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_viewport_screenshot": {}
  }
}

Questions about get_viewport_screenshot