Create a shareable WebXR AR passthrough session URL and QR code. On phone or tablet with WebXR AR support, the model is overlaid on the camera feed at the requested scale. When to use: a field user needs to walk the jobsite with a phone and see the model overlaid in-place at 1:1 scale, or drop a ...
Part of the ScanBIM MCP server.
Free to start. No card required.
AI agents invoke xr_launch_ar_session to trigger processes or run actions in ScanBIM MCP. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
xr_launch_ar_session can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"xr_launch_ar_session": {
"limits": [
{
"counter": "xr_launch_ar_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full ScanBIM MCP policy for all 19 tools.
These attack patterns abuse exactly the kind of access xr_launch_ar_session gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Create a shareable WebXR AR passthrough session URL and QR code. On phone or tablet with WebXR AR support, the model is overlaid on the camera feed at the requested scale. When to use: a field user needs to walk the jobsite with a phone and see the model overlaid in-place at 1:1 scale, or drop a tabletop mini-model on a desk. When NOT to use: the target device is a Meta Quest in VR mode — use xr_launch_vr_session. The device lacks WebXR AR (desktop browser) — use get_viewer_link. APS scopes: viewables:read data:read (enforced at viewer page load, not at tool call). Rate limits: APS default ~50 req/min per app per endpoint; Model Derivative translation jobs ~60 req/min; OSS uploads size-limited per file to 100MB for direct upload, larger via resumable. Errors: 401 APS token expired/invalid — refresh (only at viewer page load); 403 scope or resource permission denied; 404 URN not found — check the ID; 429 rate limited — backoff and retry; 5xx APS upstream outage — retry with jitter. Side effects: NON-IDEMPOTENT. Each call mints a new session_id (ar_<epoch_ms>). Inserts a row into D1 usage_log read by xr_list_sessions. No APS resources are created.. It is categorised as a Execute tool in the ScanBIM MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScanBIM MCP server in PolicyLayer and add a rule for xr_launch_ar_session: 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 ScanBIM MCP. Nothing to install.
xr_launch_ar_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the xr_launch_ar_session 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 xr_launch_ar_session. 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.
xr_launch_ar_session is provided by the ScanBIM MCP server (https://scanbim-mcp.itmartin24.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 ScanBIM MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.