Get the authenticated user (resource owner)
AI agents call inbox_get_me to retrieve information from MCP Help Scout without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves metadata about the authenticated user without any capability to modify data, execute code, delete resources, or affect other systems. The severity is low because the blast radius of misuse is minimal—an AI agent can only access already-authorized user information, which does not compromise data integrity or enable harmful actions.
From the tool's definition Tool name 'inbox_get_me' and description 'Get the authenticated user (resource owner)' indicate a simple retrieval of the current user's profile information with no modifications, side effects, or external operations.
Attacks that exploit this kind of access
Get the authenticated user (resource owner). It is categorised as a Read tool in the MCP Help Scout MCP Server, which means it retrieves data without modifying state.
Register the MCP Help Scout MCP server in PolicyLayer and add a rule for inbox_get_me: 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 MCP Help Scout. Nothing to install.
inbox_get_me 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 inbox_get_me 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 inbox_get_me. 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.
inbox_get_me is provided by the MCP Help Scout MCP server (solveitsimply/mcp-helpscout). 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 →