Display the current user
AI agents call rubeus_currentluid to retrieve information from Rubeus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval only—it queries and displays the current user's Local Unique Identifier (LUID) without side effects. It does not create, modify, delete, execute commands, or perform financial operations. While it operates within a Kerberos/security abuse toolkit (Rubeus), the specific tool itself is non-destructive and read-only.
From the tool's definition Tool name 'rubeus_currentluid' and description 'Display the current user' indicate a read-only query operation that retrieves the current user identity/LUID without modifying any state.
Attacks that exploit this kind of access
Display the current user. It is categorised as a Read tool in the Rubeus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Rubeus MCP Server MCP server in PolicyLayer and add a rule for rubeus_currentluid: 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 Rubeus MCP Server. Nothing to install.
rubeus_currentluid 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 rubeus_currentluid 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 rubeus_currentluid. 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.
rubeus_currentluid is provided by the Rubeus MCP Server MCP server (schwarztim/sec-rubeus-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 →