Set the scene environment/skybox
AI agents use set_environment 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 modifies the environment or skybox of a Three.js/Threlte scene, which is a reversible change to scene state. It does not delete data (Destructive), execute arbitrary code (Execute), trigger financial transactions (Financial), or retrieve data (Read). It aligns with Write category (creates or modifies data reversibly).
From the tool's definition Tool name: 'set_environment'; Description: 'Set the scene environment/skybox'. The verb 'Set' indicates modification of scene properties (environment/skybox configuration).
Documented attack patterns abuse exactly the kind of access set_environment 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 set_environment:
{
"version": "1",
"default": "deny",
"tools": {
"set_environment": {
"limits": [
{
"counter": "set_environment_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_environment 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.
Set the scene environment/skybox. 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 set_environment: 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.
set_environment 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 set_environment 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 set_environment. 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.
set_environment 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.