Get information about the currently authenticated user. This endpoint retrieves: - Basic user information (username, real name, email) - Assigned roles - Default app settings - User type Returns: Dict[str, Any]: Dictionary containing user information
AI agents call current_user to retrieve information from Splunk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns authenticated user metadata with no side effects. It is purely informational, fitting the Read category. Severity is low because the information returned is about the current user's own profile, which is typically already known to an authenticated session and does not expose sensitive system configuration or data beyond user identity.
From the tool's definition Tool description explicitly states it 'retrieves' user information and 'returns' a dictionary containing user details. Actions are read-only: getting username, real name, email, roles, app settings, and user type.
Documented attack patterns abuse exactly the kind of access current_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Splunk, and nothing reaches the server without passing your rules. This is the rule we recommend for current_user:
{
"version": "1",
"default": "deny",
"tools": {
"current_user": {}
}
}current_user is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get information about the currently authenticated user. This endpoint retrieves: - Basic user information (username, real name, email) - Assigned roles - Default app settings - User type Returns: Dict[str, Any]: Dictionary containing user information. It is categorised as a Read tool in the Splunk MCP Server, which means it retrieves data without modifying state.
Register the Splunk MCP server in PolicyLayer and add a rule for current_user: 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 Splunk. Nothing to install.
current_user 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 current_user 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 current_user. 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.
current_user is provided by the Splunk MCP server (livehybrid/splunk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Splunk, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Splunk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.