AI agents use memento_begin_session 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 creates a new session and closes any currently active session, which is a state-modifying write operation. Closing an active session may cause loss of unsaved session state, but is not fully irreversible in the destructive sense. Marked deprecated, which slightly lowers confidence. The blast radius is medium since it affects the active session context for the AI agent.
From the tool's definition 'Start a new Memento session for this workspace (closes any active session)'
Attacks that exploit this kind of access
[DEPRECATED] Start a new Memento session for this workspace (closes any active session). 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_begin_session: 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_begin_session 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_begin_session 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_begin_session. 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_begin_session 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 →