erase_memories
AI agents call erase_memories to permanently remove resources in Mem0 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The naming pattern 'erase_memories' (plural, aggressive verb) combined with the context of memory management operations indicates an irreversible destructive action on data. Even without a description, the semantic intent is clear: permanently remove memory records. This is more severe than the singular 'delete_memory' tool.
From the tool's definition Tool name is 'erase_memories' which indicates irreversible deletion of stored memory records. The description is empty, but the name strongly suggests a bulk or complete memory erasure operation.
Attacks that exploit this kind of access
erase_memories. It is categorised as a Destructive tool in the Mem0 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mem0 MCP server in PolicyLayer and add a rule for erase_memories: 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 Mem0. Nothing to install.
erase_memories is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the erase_memories 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 erase_memories. 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.
erase_memories is provided by the Mem0 MCP server (olk/mem0-mcp-server). 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 →