export_ar
Turn any public GLB URL into a one-tap "View in your space" experience. The returned link routes itself by device: Apple Quick Look on iPhone and iPad, Google Scene Viewer on Android, an interactive WebGL viewer on desktop. Use it right after generating or finding a model so the person can put it...
This record as markdown: /tools/3d-ar-studio-mcp/export-ar.md
What export_ar does on 3d Ar Studio
AI agents use export_ar to create or update resources in 3d Ar Studio, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 3d Ar Studio environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
kind | string | — | avatar marks a rigged character, which stays animated. |
title | string | — | Name shown in the AR experience. |
glb_url | string | Yes | Public https URL of a .glb or .gltf model. |
user_agent | string | — | If you know the viewer's User-Agent, the response names the viewer they will get. |
Parameters from the server's own tool schema.
Why export_ar is rated Medium
An AI agent can call export_ar faster than any human can review: one bad instruction and it creates or modifies resources in 3d Ar Studio by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs export_ar safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 3d Ar Studio, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For export_ar, this is the rule to start with:
export_ar 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.
The button opens the PolicyLayer dashboard: create your workspace, connect 3d Ar Studio, apply this rule, and every export_ar call is checked against it from then on.
Questions about export_ar
Turn any public GLB URL into a one-tap "View in your space" experience. The returned link routes itself by device: Apple Quick Look on iPhone and iPad, Google Scene Viewer on Android, an interactive WebGL viewer on desktop. Use it right after generating or finding a model so the person can put it on their actual desk. It is categorised as a Write tool in the 3d Ar Studio MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
export_ar accepts 4 parameters: kind, title, glb_url, user_agent. Required: glb_url. The full parameter table on this page comes from the server's own tool schema.
Register the 3d Ar Studio MCP server in PolicyLayer and add a rule for export_ar: 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 3d Ar Studio. Nothing to install.
export_ar 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 export_ar 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 export_ar. 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.
export_ar is provided by the 3d Ar Studio MCP server (3d-ar-studio-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 3d Ar Studio, and thousands of servers like it.
This server
Across the catalogue