Returns information about the current user WHAT: Returns information about the current authenticated user. WHEN TO USE: 1. When you need any details about the user 2. When you want to validate the user's preferences or settings 3. At the start of a conversation to understand user context BEHAVIOR...
AI agents call get_current_user to retrieve information from Forgetful without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward information retrieval operation that queries and returns user metadata. It performs no mutations, deletions, or external operations. The only data accessed is the authenticated user's own profile information, limiting the blast radius if misused. Classified as Read with low severity.
From the tool's definition Tool returns information about the current authenticated user with fields like id, external_id, name, email, notes, timestamps.
Documented attack patterns abuse exactly the kind of access get_current_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgetful, and nothing reaches the server without passing your rules. This is the rule we recommend for get_current_user:
{
"version": "1",
"default": "deny",
"tools": {
"get_current_user": {}
}
}get_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.
Returns information about the current user WHAT: Returns information about the current authenticated user. WHEN TO USE: 1. When you need any details about the user 2. When you want to validate the user's preferences or settings 3. At the start of a conversation to understand user context BEHAVIOR: - Returns a User object containing information about the authenticated user - Includes fields like id, external_id, name, email, notes, timestamps - Auto-provisions user if they don't exist (when AUTH_ENABLED=false) WHEN NOT TO USE: - When you already have cached user context - When the request does not require information about the user or their preferences - During repeated operations where user data hasn't changed. It is categorised as a Read tool in the Forgetful MCP Server, which means it retrieves data without modifying state.
Register the Forgetful MCP server in PolicyLayer and add a rule for get_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 Forgetful. Nothing to install.
get_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 get_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 get_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.
get_current_user is provided by the Forgetful MCP server (scottrbk/forgetful). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
59 Forgetful tools catalogued and risk-classified — across an index of 42,500+ MCP servers.