AI agents use memento_resume_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 restores a previous checkpoint and creates a new active session, which constitutes writing/modifying state (session data, memory state, L1 cache). It is reversible in nature (resuming/restoring rather than deleting), placing it in the Write category. Medium severity because restoring an incorrect or malicious session checkpoint could corrupt the agent's active memory context.
From the tool's definition Resume from a previous session_id by restoring its checkpoint (including L1) and opening a new active session
Attacks that exploit this kind of access
[DEPRECATED] Resume from a previous session_id by restoring its checkpoint (including L1) and opening a new 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_resume_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_resume_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_resume_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_resume_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_resume_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 →