AI agents invoke stopAnimation to trigger actions in Maige 3d. 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.
While stopping an animation is reversible (another animation can be started), it is an action that executes external operations whose effects depend on which object and animation context is provided. This fits Execute rather than Write because it is triggering a behavioral change in a running system rather than creating or modifying persistent data.
From the tool's definition Tool name is 'stopAnimation' and description states it will 'Stop any running animation on an object.' This directly triggers an action that modifies the state of a 3D scene by halting an ongoing process.
Attacks that exploit this kind of access
Stop any running animation on an object. It is categorised as a Execute tool in the Maige 3d MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Maige 3d MCP server in PolicyLayer and add a rule for stopAnimation: 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.
stopAnimation 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 stopAnimation 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 stopAnimation. 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.
stopAnimation 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 →