AI agents call get_instance_children to retrieve information from Melo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves hierarchical data from Roblox Studio without side effects. It is a straightforward query operation that traverses the instance tree and returns metadata. The 'list' operation is a canonical Read action. Even in the context of an agentic Roblox development server, viewing instance hierarchy poses minimal risk of misuse.
From the tool's definition Tool name and description indicate it 'List[s] immediate children of an instance' with a read-only return of array of {name, className} children. No mutation, creation, or deletion occurs.
Attacks that exploit this kind of access
List immediate children of an instance. Args: - path (string): Instance path Returns: Array of { name, className } children. It is categorised as a Read tool in the Melo MCP Server, which means it retrieves data without modifying state.
Register the Melo MCP server in PolicyLayer and add a rule for get_instance_children: 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 Melo. Nothing to install.
get_instance_children 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_instance_children 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_instance_children. 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_instance_children is provided by the Melo MCP server (yannyhl/linkedsword-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →