Delete an episode from the graph memory.
AI agents call delete_episode to permanently remove resources in local-RAG-backend — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion operation on stored graph memory data. Once an episode is deleted, it cannot be recovered through normal means. This qualifies as Destructive rather than Write because deletion cannot be undone.
From the tool's definition Tool name contains 'delete' and description states 'Delete an episode from the graph memory' — indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete an episode from the graph memory. It is categorised as a Destructive tool in the local-RAG-backend MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the local-RAG-backend MCP server in PolicyLayer and add a rule for delete_episode: 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 local-RAG-backend. Nothing to install.
delete_episode 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_episode 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_episode. 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_episode is provided by the local-RAG-backend MCP server (suwa-sh/local-rag-backend). 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 →