AI agents use memento_toggle_access 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.
This tool modifies the access control state of the memory system, which is a reversible configuration change. While marked as deprecated, toggling between access modes (read-write, read-only, lockdown) constitutes writing/updating system state. It does not permanently delete data (Destructive), execute arbitrary code (Execute), or move money (Financial).
From the tool's definition Tool description states it 'toggles the access state' of the Memento memory provider between 'read-write, read-only, lockdown' modes. The verb 'toggle' indicates modifying configuration state.
Attacks that exploit this kind of access
[DEPRECATED] Toggle the access state of the Memento memory provider (read-write, read-only, lockdown). 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_toggle_access: 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_toggle_access 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_toggle_access 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_toggle_access. 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_toggle_access 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 →