AI agents call memento_get_pending_notifications to retrieve information from Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries pending notifications and memory events from the Memento system without side effects. It is a read-only operation that returns context alerts. No data is modified, deleted, or executed. The deprecation status does not change its classification but may slightly reduce concern about its active use.
From the tool's definition Tool name 'memento_get_pending_notifications' and description 'Get pending proactive notifications' indicate retrieval of existing notifications and memory events with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
[DEPRECATED] Get pending proactive notifications — relevant context alerts and memory events. It is categorised as a Read tool in the Memento MCP Server, which means it retrieves data without modifying state.
Register the Memento MCP server in PolicyLayer and add a rule for memento_get_pending_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 Memento. Nothing to install.
memento_get_pending_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 memento_get_pending_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 memento_get_pending_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.
memento_get_pending_notifications is provided by the Memento MCP server (joyciakira/memento). 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 →