Delete a memory item by its UUID.
AI agents call delete to permanently remove resources in Arca MCP — 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 a memory item identified by UUID. This is a destructive action that cannot be undone and removes data permanently from the vector storage system. While the blast radius may be limited to a single memory item (lower than system-wide deletion), the irreversible nature of the operation places it in the Destructive category, which takes precedence over Write.
From the tool's definition Tool name is 'delete' and description states 'Delete a memory item by its UUID' - this irreversibly removes stored data without possibility of recovery through the tool interface.
Attacks that exploit this kind of access
Delete a memory item by its UUID. It is categorised as a Destructive tool in the Arca MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Arca MCP server in PolicyLayer and add a rule for 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 Arca MCP. Nothing to install.
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 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 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.
delete is provided by the Arca MCP server (m0nochr0me/arca-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 →