AI agents use session_extract to create or update resources in Mementos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mementos environment.
This tool creates new structured memory entries from a session summary, which is a Write operation (auto-creates data). It does not delete or overwrite existing data irreversibly, nor does it execute code or involve financial transactions. Severity is medium because an AI agent misusing it could populate the memory system with incorrect or misleading structured memories, affecting future agent behavior.
From the tool's definition 'Extract memories from a session summary. Auto-creates structured memories from title, topics, notes.'
Attacks that exploit this kind of access
Extract memories from a session summary. Auto-creates structured memories from title, topics, notes. It is categorised as a Write tool in the Mementos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mementos MCP server in PolicyLayer and add a rule for session_extract: 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 Mementos. Nothing to install.
session_extract 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 session_extract 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 session_extract. 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.
session_extract is provided by the Mementos MCP server (@hasna/mementos). 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 →