Remove a stored memory entry by exact (namespace, key). Use when a previously stored decision is invalidated or contains stale data. No native equivalent — Write to a file does not affect the .swarm/memory.db SQLite store.
AI agents call memory_delete to permanently remove resources in Claude Flow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although framed as 'invalidating' stale data, this tool permanently deletes records from a shared swarm memory database. In a multi-agent system, unauthorized or mistaken deletion of memory entries could cause cascading failures (lost decision context, corrupted agent coordination state) and cannot be undone. This is more severe than Write (which is reversible) and qualifies as Destructive.
From the tool's definition The tool explicitly performs removal/deletion of data ('Remove a stored memory entry'), operates on a persistent database (.swarm/memory.db SQLite store), and is described as irreversible (deletion).
Attacks that exploit this kind of access
Remove a stored memory entry by exact (namespace, key). Use when a previously stored decision is invalidated or contains stale data. No native equivalent — Write to a file does not affect the .swarm/memory.db SQLite store. It is categorised as a Destructive tool in the Claude Flow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Flow 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 Flow. 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 Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.