AI agents use updateParticles to create or update resources in Maige 3d — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maige 3d environment.
This tool modifies existing 3D scene data (particle system properties) but does not delete, destroy, or irreversibly remove objects. Updates to particle properties (emission rate, color, velocity, etc.) are reversible through subsequent updates. While it affects a live 3D scene, the blast radius is limited to visual/aesthetic changes within that scene context, typical of Write-category tools.
From the tool's definition Tool is named 'updateParticles' and described as 'Update properties of an existing particle system.' The verb 'update' and action of modifying particle system properties indicates data modification of a reversible nature.
Attacks that exploit this kind of access
Update properties of an existing particle system. It is categorised as a Write tool in the Maige 3d MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Maige 3d MCP server in PolicyLayer and add a rule for updateParticles: 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.
updateParticles is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the updateParticles 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 updateParticles. 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.
updateParticles 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 →