Delete memory (soft delete - data retained).
AI agents call delete_memory to permanently remove resources in Code Graph Knowledge System — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although described as a 'soft delete', the tool irreversibly removes data from the knowledge graph's memory. Soft-delete still prevents recovery through normal API operations and constitutes an unrecoverable action from the user's perspective. In the context of a code knowledge graph, deleting memory entries could remove critical analysis results, dependency mappings, or documentation relationships.
From the tool's definition Tool name 'delete_memory' explicitly performs a delete operation. Description states 'Delete memory (soft delete - data retained)' - the term 'delete' combined with the action of removing memory entries represents an irreversible data removal action, even if…
Documented attack patterns abuse exactly the kind of access delete_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Graph Knowledge System, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_memory:
{
"version": "1",
"default": "deny",
"hide": [
"delete_memory"
]
}delete_memory disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete memory (soft delete - data retained). It is categorised as a Destructive tool in the Code Graph Knowledge System MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Code Graph Knowledge System MCP server in PolicyLayer and add a rule for delete_memory: 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 Code Graph Knowledge System. Nothing to install.
delete_memory 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_memory 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_memory. 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_memory is provided by the Code Graph Knowledge System MCP server (royisme/codebase-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Graph Knowledge System, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Code Graph Knowledge System tools catalogued and risk-classified — across an index of 43,000+ MCP servers.