AI agents call search 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 performs a search query across the Roblox instance tree to retrieve matching instances based on name and class filters. It has no side effects—it only returns data without modifying, deleting, or executing anything. Despite the debug/inspection context of the server (which includes more dangerous tools like fire_remote, invoke_remote, and get_source), this specific tool is purely informational.
From the tool's definition Tool description states it 'recursively search instances by name substring (and optional className)' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Recursively search instances by name substring (and optional className), capped by limit. Defaults to 100 results. 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 search: 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.
search 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 search 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 search. 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.
search 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 →