Elimina múltiples memorias por id en una sola transacción SQLite. Informa cuántas se eliminaron y cuáles ids no se encontraron.
AI agents call delete_memories to permanently remove resources in Engram — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes structured memory records from the SQLite database without reversibility. Once memories are deleted via this tool, they cannot be recovered through normal application operations. This is a destructive operation affecting persistent agent context storage.
From the tool's definition delete_memories: 'Elimina múltiples memorias por id en una sola transacción SQLite' (Deletes multiple memories by id in a single SQLite transaction).
Attacks that exploit this kind of access
Elimina múltiples memorias por id en una sola transacción SQLite. Informa cuántas se eliminaron y cuáles ids no se encontraron. It is categorised as a Destructive tool in the Engram MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Engram MCP server in PolicyLayer and add a rule for delete_memories: 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 Engram. Nothing to install.
delete_memories 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_memories 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_memories. 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_memories is provided by the Engram MCP server (jacksini/engram-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 →