删除所有记忆
AI agents call delete_all_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.
This tool permanently removes all memories without individual selection or recovery option, fitting the Destructive category as it irreversibly deletes data at scale. While not as critical as wiping entire databases with financial impact, the bulk deletion of all user memories represents a high-severity operation that cannot be undone and would cause significant data loss if invoked by a misaligned agent.
From the tool's definition Tool name 'delete_all_memories' and description '删除所有记忆' (Chinese: 'delete all memories') indicate irreversible deletion of all stored memory records.
Attacks that exploit this kind of access
删除所有记忆. 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 delete_all_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.
delete_all_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 delete_all_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 delete_all_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.
delete_all_memories is provided by the Mem0 MCP server (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 →