AI agents use set_property to create or update resources in Dex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dex environment.
This tool creates or modifies data reversibly—it updates instance properties within a Roblox game session. While property changes could have significant game-logic consequences (high severity), the operation is not irreversible (not Destructive) and does not execute arbitrary code (not Execute).
From the tool's definition Tool name is 'set_property' and description states 'Set a property on an instance by ref.' This is a modification operation that changes instance state in a Roblox client.
Attacks that exploit this kind of access
Set a property on an instance by ref. The value is coerced to the property. It is categorised as a Write tool in the Dex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dex MCP server in PolicyLayer and add a rule for set_property: 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.
set_property is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_property 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 set_property. 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.
set_property 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 →