Get recent notifications.
AI agents call moltbook_get_notifications to retrieve information from Moltbook MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves notification data from the Moltbook platform. It performs a query operation that does not create, modify, delete, or execute any external actions. The only potential information exposure is to the user's own notifications, which is a standard and expected read operation in social platforms. Classification as Read with low severity is appropriate.
From the tool's definition Tool name 'moltbook_get_notifications' and description 'Get recent notifications' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get recent notifications. It is categorised as a Read tool in the Moltbook MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Moltbook MCP Server MCP server in PolicyLayer and add a rule for moltbook_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 Moltbook MCP Server. Nothing to install.
moltbook_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 moltbook_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 moltbook_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.
moltbook_get_notifications is provided by the Moltbook MCP Server MCP server (thebenlamm/moltbook-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 →