Soft-delete a memory. Always confirm with the user before deleting.
AI agents call memory_delete to permanently remove resources in Claude Crowed — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes stored memories from a persistent document store. Although labeled 'soft-delete' and accompanied by a recovery mechanism (memory_undelete), it still represents data deletion—an operation that cannot be undone in the moment and removes access to stored research, design decisions, and codebase insights.
From the tool's definition Tool name 'memory_delete' combined with description stating it performs a 'Soft-delete a memory.' The term 'delete' indicates irreversible removal of data from the semantic memory system, even though it is characterized as 'soft-delete' (which may allow…
Attacks that exploit this kind of access
Soft-delete a memory. Always confirm with the user before deleting. It is categorised as a Destructive tool in the Claude Crowed MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Crowed 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 Claude Crowed. 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 Claude Crowed MCP server (thenewjavaman/claude-crowed). 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 →