Add a GLTF/GLB model to the scene (A-Frame or Three.js)
AI agents use scene_add_gltf_model to create or update resources in 8th Wall MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 8th Wall MCP Server environment.
This tool creates or modifies the AR scene state by inserting 3D model assets into the scene graph. While this changes the scene structure, it is reversible (models can be removed, scenes reset, or projects reverted), so it does not meet the Destructive threshold.
From the tool's definition Tool explicitly performs 'Add a GLTF/GLB model to the scene' — a creation action that modifies the AR scene composition by introducing new 3D assets. The verb 'Add' and the scope of modifying scene state classify this as a Write operation.
Documented attack patterns abuse exactly the kind of access scene_add_gltf_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 8th Wall MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for scene_add_gltf_model:
{
"version": "1",
"default": "deny",
"tools": {
"scene_add_gltf_model": {
"limits": [
{
"counter": "scene_add_gltf_model_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}scene_add_gltf_model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add a GLTF/GLB model to the scene (A-Frame or Three.js). It is categorised as a Write tool in the 8th Wall MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 8th Wall MCP Server MCP server in PolicyLayer and add a rule for scene_add_gltf_model: 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 8th Wall MCP Server. Nothing to install.
scene_add_gltf_model 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 scene_add_gltf_model 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 scene_add_gltf_model. 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.
scene_add_gltf_model is provided by the 8th Wall MCP Server MCP server (superdwayne/8thwallmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 8th Wall MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
64 8th Wall MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.