Low Risk

get_node_reference

Returns the full API reference for a specific SceneView node type or composable — parameters, types, and a usage example — parsed directly from the official llms.txt. Use this when you need the exact signature or options for a node (e.g. ModelNode, LightNode, ARScene). If the requested type is no...

Part of the SceneView 3D & AR server.

get_node_reference is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE SCENEVIEW 3D & AR →

Free to start. No card required.

AI agents call get_node_reference to retrieve information from SceneView 3D & AR without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though get_node_reference only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_node_reference": {}
  }
}

See the full SceneView 3D & AR policy for all 63 tools.

Get this rule live on your own SceneView 3D & AR server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SCENEVIEW 3D & AR →

View all 63 tools →

These attack patterns abuse exactly the kind of access get_node_reference gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so get_node_reference only ever does what you allow.

SECURE SCENEVIEW 3D & AR →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the get_node_reference tool do? +

Returns the full API reference for a specific SceneView node type or composable — parameters, types, and a usage example — parsed directly from the official llms.txt. Use this when you need the exact signature or options for a node (e.g. ModelNode, LightNode, ARScene). If the requested type is not found, the response lists all available types.. It is categorised as a Read tool in the SceneView 3D & AR MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_node_reference? +

Register the SceneView 3D & AR MCP server in PolicyLayer and add a rule for get_node_reference: 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 SceneView 3D & AR. Nothing to install.

What risk level is get_node_reference? +

get_node_reference is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_node_reference? +

Yes. Add a rate_limit block to the get_node_reference 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.

How do I block get_node_reference completely? +

Set action: deny in the PolicyLayer policy for get_node_reference. 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.

What MCP server provides get_node_reference? +

get_node_reference is provided by the SceneView 3D & AR MCP server (sceneview/gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SceneView 3D & AR tool call.

Deterministic rules across all 63 SceneView 3D & AR 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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.