Delete a memory by name.
AI agents call memory_delete to permanently remove resources in Terminal — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Memory deletion is a destructive operation that permanently removes data. While the blast radius is somewhat contained (limited to stored memories rather than system files or critical data), deletion operations are inherently irreversible and warrant the Destructive category.
From the tool's definition Tool name explicitly includes 'delete' and description states 'Delete a memory by name.' The action is irreversible—once a memory is deleted, it cannot be recovered without external backups.
Attacks that exploit this kind of access
Delete a memory by name. It is categorised as a Destructive tool in the Terminal MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Terminal MCP server in PolicyLayer and add a rule for memory_delete: 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 Terminal. Nothing to install.
memory_delete 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 memory_delete 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_delete. 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_delete is provided by the Terminal MCP server (koushikmaji31/terminal-mcp-agent). 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 →