STORE: delete a vector by id from a namespace, scoped to...
AI agents call store.vector-delete to permanently remove resources in Mcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes stored data (a vector) by identifier. While the blast radius is scoped to a namespace and the data may be recoverable through backups, the operation itself cannot be undone by the tool and represents irreversible data destruction. This qualifies as Destructive rather than Write.
From the tool's definition Tool name contains 'delete' and description states 'delete a vector by id from a namespace' — this is an irreversible removal operation.
Attacks that exploit this kind of access
STORE: delete a vector by id from a namespace, scoped to. It is categorised as a Destructive tool in the Mcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP server in PolicyLayer and add a rule for store.vector-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 Mcp. Nothing to install.
store.vector-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 store.vector-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 store.vector-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.
store.vector-delete is provided by the MCP server (@2sio/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 →