scene_get_tree
Return the node tree of the currently edited scene (name, type, path, script, children).
This record as markdown: /tools/breakpoint-mcp/scene-get-tree.md
What scene_get_tree does on Breakpoint
AI agents call scene_get_tree to retrieve information from Breakpoint without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
max_depth | integer | — | Max recursion depth (default 64) |
Parameters from the server's own tool schema.
Why scene_get_tree is rated Low
This tool retrieves hierarchical structural information about a scene without side effects. It queries and returns data about existing nodes, their properties, and relationships. No data is created, modified, deleted, or executed. This is a classic Read operation with minimal risk—an AI agent querying scene structure poses no threat to data integrity or system state.
From the tool's definition Tool returns scene node tree data (name, type, path, script, children) with no indication of modification, deletion, or execution capabilities. The verb 'get' and passive retrieval operation confirm this is a read-only query.
Attacks that exploit this kind of access
The rule that runs scene_get_tree safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scene_get_tree, this is the rule to start with:
scene_get_tree is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every scene_get_tree call is checked against it from then on.
Questions about scene_get_tree
Return the node tree of the currently edited scene (name, type, path, script, children). It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
scene_get_tree accepts 1 parameter: max_depth. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for scene_get_tree: 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 Breakpoint. Nothing to install.
scene_get_tree 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 scene_get_tree 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 scene_get_tree. 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.
scene_get_tree is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue