Save/upsert a memory. scope: global=all agents, shared=project, private=single agent, working=transient session scratchpad (auto-expires in 1h, excluded from ALMA synthesis). conflict controls what happens when key already exists.
AI agents use memory_save 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 or modifies memory records across different scopes (global, shared, private, working). While it does not delete or irreversibly destroy data, and does not execute arbitrary code or move money, it does persistently alter the agent's memory state. The multi-scope nature (global affecting all agents) elevates severity to medium, as widespread memory corruption could significantly impact agent behavior.
From the tool's definition Tool description explicitly states "Save/upsert a memory" — upsert is a standard write operation (insert or update). The 'conflict' parameter controls handling of existing keys, indicating reversible modification of data.
Attacks that exploit this kind of access
Save/upsert a memory. scope: global=all agents, shared=project, private=single agent, working=transient session scratchpad (auto-expires in 1h, excluded from ALMA synthesis). conflict controls what happens when key already exists. 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: 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 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 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. 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 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 →