AI agents use memento_dismiss_notification to create or update resources in Memento — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memento environment.
Dismissing a notification is a reversible state change (modifying notification status), not a permanent deletion. It falls under Write as it updates the notification's visibility state. Severity is low since notifications are non-critical UI state. Confidence is slightly reduced because the description is marked DEPRECATED and minimal detail is given.
From the tool's definition 'Dismiss a notification so it no longer appears' — marks a notification as dismissed/read, modifying its state
Attacks that exploit this kind of access
[DEPRECATED] Dismiss a notification so it no longer appears. It is categorised as a Write tool in the Memento MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memento MCP server in PolicyLayer and add a rule for memento_dismiss_notification: 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_dismiss_notification is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memento_dismiss_notification 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_dismiss_notification. 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_dismiss_notification 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 →