This record as markdown: /tools/caravanglory-cocos-mcp-server/get-node-tree.md
What get_node_tree does on Cocos
AI agents call get_node_tree to retrieve information from Cocos without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_node_tree is rated Low
This tool retrieves and queries the node tree structure from the Cocos Creator editor for inspection and debugging purposes. It has no side effects, does not modify data, and does not trigger external operations. It is a pure read operation with minimal security risk - at worst an agent could inspect internal scene structure but cannot alter or delete anything.
From the tool's definition Tool name 'get_node_tree' and description 'Get detailed node tree for debugging' indicate retrieval of scene/node hierarchy information without modification. Verb 'get' is characteristic of Read operations.
Attacks that exploit this kind of access
The rule that runs get_node_tree safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cocos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_node_tree, this is the rule to start with:
get_node_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 Cocos, apply this rule, and every get_node_tree call is checked against it from then on.
Questions about get_node_tree
Get detailed node tree for debugging. It is categorised as a Read tool in the Cocos MCP Server, which means it retrieves data without modifying state.
Register the Cocos MCP server in PolicyLayer and add a rule for get_node_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 Cocos. Nothing to install.
get_node_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 get_node_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 get_node_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.
get_node_tree is provided by the Cocos MCP server (caravanglory/cocos-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cocos, and thousands of servers like it.
This server
Across the catalogue