AI agents call delete_memory to permanently remove resources in Robust Long-Term Memory MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
delete_memory removes data that cannot be undone. Despite the empty description, the tool name combined with the server's SQLite-backed persistent memory architecture makes the destructive intent unambiguous. This ranks higher than Write (which are reversible) and Execute (which may have side effects but are not inherently irreversible).
From the tool's definition Tool named 'delete_memory' on a persistent memory system using SQLite. The name and context clearly indicate irreversible deletion of stored memory records.
Documented attack patterns abuse exactly the kind of access delete_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Robust Long-Term Memory MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_memory:
{
"version": "1",
"default": "deny",
"hide": [
"delete_memory"
]
}delete_memory disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
delete_memory. It is categorised as a Destructive tool in the Robust Long-Term Memory MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Robust Long-Term Memory MCP server in PolicyLayer and add a rule for delete_memory: 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 Robust Long-Term Memory MCP. Nothing to install.
delete_memory 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_memory 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_memory. 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_memory is provided by the Robust Long-Term Memory MCP server (rotoslider/long-term-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Robust Long-Term Memory MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Robust Long-Term Memory MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.