Delete a memory by ID.
AI agents call delete_memory to permanently remove resources in mcp-Agentmemory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (a memory record) from the system by ID. Deletion is irreversible and cannot be undone through normal means. While the blast radius is bounded to individual memory records rather than full system destruction, any unauthorized or mistaken deletion of memories—particularly in an AI agent context where memories are used for context and decision-making—could have significant…
From the tool's definition Tool name is 'delete_memory' with description 'Delete a memory by ID.' The verb 'delete' combined with operation on stored memory data indicates irreversible removal.
Attacks that exploit this kind of access
Delete a memory by ID. It is categorised as a Destructive tool in the mcp-Agentmemory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the mcp-Agentmemory 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 mcp-Agentmemory. 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 mcp-Agentmemory MCP server (obidel/agentmemory). 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 →