Delete a memory by ID or by context match. Use this when the user wants to remove a memory. Can specify either: - id: Direct memory ID (from memory_list) - context: A description of the memory to delete (will find best match) At least one of id or context must be provided.
AI agents call memory_delete to permanently remove resources in Cursor Memory MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes data from a persistent storage system without the ability to undo the operation. Deletion is irreversible and represents a loss of information that the AI assistant relies on across sessions. While the blast radius is somewhat limited to user context/preferences rather than critical system data, the irreversible nature of deletion places it in the Destructive category rather than Write.
From the tool's definition The tool description explicitly states "Delete a memory by ID" and "remove a memory". The name itself is "memory_delete". The operation is irreversible—deleted memories cannot be recovered from the SQLite-backed persistent storage.
Attacks that exploit this kind of access
Delete a memory by ID or by context match. Use this when the user wants to remove a memory. Can specify either: - id: Direct memory ID (from memory_list) - context: A description of the memory to delete (will find best match) At least one of id or context must be provided. It is categorised as a Destructive tool in the Cursor Memory MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cursor Memory MCP Server 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 Cursor Memory MCP Server. 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 Cursor Memory MCP Server MCP server (willard-jana/cursor-memory-mcp). 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 →