Get the logged-in user
AI agents call GET_USER_NOTIFICATIONS to retrieve information from Travel Agent MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves user information (notifications and logged-in user identity) without creating, modifying, or deleting data. This is a straightforward read operation with minimal blast radius—disclosure of user notification data is a privacy concern but not destructive or executable.
From the tool's definition Tool name 'GET_USER_NOTIFICATIONS' and description 'Get the logged-in user' indicate a retrieval operation with no side effects. This fetches user identity/notification data without modifying, deleting, or executing external actions.
Attacks that exploit this kind of access
Get the logged-in user. It is categorised as a Read tool in the Travel Agent MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Travel Agent MCP Server MCP server in PolicyLayer and add a rule for GET_USER_NOTIFICATIONS: 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 Travel Agent MCP Server. Nothing to install.
GET_USER_NOTIFICATIONS 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_USER_NOTIFICATIONS 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_USER_NOTIFICATIONS. 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_USER_NOTIFICATIONS is provided by the Travel Agent MCP Server MCP server (nxgnosis/travelagentmcp). 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 →