AI agents call takeScreenshot to retrieve information from Maige 3d without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
takeScreenshot retrieves the current visual state of the 3D scene and returns it as image data without modifying, executing operations, or affecting underlying scene data. This is a passive observation operation with no side effects, fitting the Read category (retrieves data; no side effects).
From the tool's definition Tool captures and returns current viewport state as 'base-64 PNG data URL' with no modification or deletion capabilities. The verb 'capture' and return of image data indicates data retrieval only.
Attacks that exploit this kind of access
Capture the current 3D viewport and return a base-64 PNG data URL. Requires a browser client to be connected. It is categorised as a Read tool in the Maige 3d MCP Server, which means it retrieves data without modifying state.
Register the Maige 3d MCP server in PolicyLayer and add a rule for takeScreenshot: 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 Maige 3d. Nothing to install.
takeScreenshot 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 takeScreenshot 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 takeScreenshot. 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.
takeScreenshot is provided by the Maige 3d MCP server (m-ai-gexr/mcp-webgpu). 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 →