Add a 3D model (GLB/GLTF) from assets to the scene
AI agents use desktop_add_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 project state by inserting a 3D model into an active scene. This is a Write operation because it changes the composition of the AR experience reversibly (models can be removed/replaced later). While it affects the scene, it does not execute arbitrary code, destroy data, or create financial obligations.
From the tool's definition Tool adds/modifies 3D models to a scene ('Add a 3D model... from assets to the scene'), which creates or modifies data within the AR experience project.
Documented attack patterns abuse exactly the kind of access desktop_add_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 desktop_add_model:
{
"version": "1",
"default": "deny",
"tools": {
"desktop_add_model": {
"limits": [
{
"counter": "desktop_add_model_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}desktop_add_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 3D model (GLB/GLTF) from assets to the scene. 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 desktop_add_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.
desktop_add_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 desktop_add_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 desktop_add_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.
desktop_add_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.