AI agents use memory_sync_push 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.
The tool creates or modifies data on a remote server through push synchronization. This is reversible (data can be updated, deleted, or re-synced), so it does not meet the Destructive threshold. It does not execute arbitrary code or shell commands, so it is not Execute. The primary action is data modification/upload, making Write the appropriate category.
From the tool's definition Tool description states it will 'Push local memories to a remote mementos-serve instance', which modifies state on a remote system by uploading/synchronizing data.
Attacks that exploit this kind of access
Push local memories to a remote mementos-serve instance. Set MEMENTOS_REMOTE_URL or pass url. 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_sync_push: 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_sync_push 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_sync_push 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_sync_push. 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_sync_push 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 →