Load a GLTF/GLB model into the scene
AI agents use load_asset to create or update resources in Threlte — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Threlte environment.
This tool creates/adds a new 3D asset into the scene, which is a reversible write operation. It does not delete or overwrite existing data, execute arbitrary code, or involve financial transactions. The blast radius is medium since loading malicious or large assets could affect scene stability, but it's generally reversible by removing the loaded object.
From the tool's definition Load a GLTF/GLB model into the scene
Documented attack patterns abuse exactly the kind of access load_asset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Threlte, and nothing reaches the server without passing your rules. This is the rule we recommend for load_asset:
{
"version": "1",
"default": "deny",
"tools": {
"load_asset": {
"limits": [
{
"counter": "load_asset_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}load_asset 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.
Load a GLTF/GLB model into the scene. It is categorised as a Write tool in the Threlte MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Threlte MCP server in PolicyLayer and add a rule for load_asset: 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 Threlte. Nothing to install.
load_asset 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 load_asset 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 load_asset. 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.
load_asset is provided by the Threlte MCP server (serifeusstudio/threlte-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Threlte, 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.
30 Threlte tools catalogued and risk-classified — across an index of 43,000+ MCP servers.