AI agents use memory_save_tool_event 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 memory records (events and lessons) and modifies shared memory state. These are write operations typical of a logging/memory system—reversible via update or deletion mechanisms (as evidenced by sibling tools like 'bulk_forget' and 'entity_delete').
From the tool's definition Tool description states 'Record a tool call event' and 'saves a lesson as a shared memory', indicating creation and modification of event/memory records without permanent deletion.
Attacks that exploit this kind of access
Record a tool call event (success/failure, latency, tokens). Optionally saves a lesson as a shared memory. 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 memory_save_tool_event: 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.
memory_save_tool_event 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 memory_save_tool_event 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 memory_save_tool_event. 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.
memory_save_tool_event 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 →