Search for objects by name, type, or userData properties
AI agents call find_objects to retrieve information from Threlte without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves or queries data from the Three.js/Threlte scene without creating, modifying, deleting, or executing any code. It is a pure read operation that searches for objects based on specified criteria. The blast radius of misuse is minimal—an attacker could enumerate scene structure but cannot cause irreversible changes or execute arbitrary logic.
From the tool's definition Tool name and description: 'Search for objects by name, type, or userData properties' — a search/query operation with no modification or deletion capability.
Documented attack patterns abuse exactly the kind of access find_objects 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 find_objects:
{
"version": "1",
"default": "deny",
"tools": {
"find_objects": {}
}
}find_objects is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for objects by name, type, or userData properties. It is categorised as a Read tool in the Threlte MCP Server, which means it retrieves data without modifying state.
Register the Threlte MCP server in PolicyLayer and add a rule for find_objects: 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.
find_objects is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find_objects 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 find_objects. 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.
find_objects 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.