AI agents call get_root to retrieve information from Dex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural information about the Roblox instance hierarchy. It performs a query operation returning metadata about the game state without creating, modifying, executing code, deleting data, or triggering external effects.
From the tool's definition Tool description states 'Get the root instance' and 'top-level services' — a retrieval operation with no modification. Sibling tools like get_properties, get_children, and get_source reinforce this is part of the Read category tooling on this server.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get the root instance (game, ref 0) and its top-level services. It is categorised as a Read tool in the Dex MCP Server, which means it retrieves data without modifying state.
Register the Dex MCP server in PolicyLayer and add a rule for get_root: 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 Dex. Nothing to install.
get_root 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_root 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_root. 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_root is provided by the Dex MCP server (sanztheo/dex-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 →