AI agents call get_properties 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.
The tool retrieves property metadata from a Roblox instance without side effects, which is characteristic of a Read operation. Severity is elevated to medium rather than low due to the context: this is a debug/inspection tool for Roblox projects that could expose sensitive game logic, instance hierarchies, or internal state if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Read the properties of an instance by ref'; this is a retrieval operation with no modification.
Attacks that exploit this kind of access
Read the properties of an instance by ref. Property names come from the cached Roblox API dump when available. 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_properties: 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_properties 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_properties 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_properties. 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_properties 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 →