get_notifications
AI agents call get_notifications to retrieve information from USCardForum MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name and context establish this as a read operation that retrieves existing notification data for an authenticated user. No side effects, modifications, or irreversible actions are indicated. Low severity due to limited blast radius—notifications are typically user-specific metadata without system-wide impact.
From the tool's definition Tool name 'get_notifications' indicates retrieval of notification data. The server description states the tool is for 'managing authenticated actions like notifications and bookmarks,' positioning it within read/retrieval operations.
Attacks that exploit this kind of access
get_notifications. It is categorised as a Read tool in the USCardForum MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USCardForum MCP Server MCP server in PolicyLayer and add a rule for get_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 USCardForum MCP Server. Nothing to install.
get_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_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_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_notifications is provided by the USCardForum MCP Server MCP server (rhettlong/uscardforum-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 →