STORE: delete a key/value you stored, scoped to YOUR wallet.
AI agents call store.kv-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.
This tool performs an irreversible delete operation on stored key-value data. While the impact is scoped to the user's own wallet, deletion cannot be undone, making it Destructive rather than Write. High severity because accidental or malicious deletion of stored data could result in permanent loss, though the blast radius is limited to the user's own KV store.
From the tool's definition Tool description explicitly states "delete a key/value" — irreversible deletion of stored data. The phrase "you stored" indicates user-controlled data removal.
Attacks that exploit this kind of access
STORE: delete a key/value you stored, scoped to YOUR wallet. 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.kv-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.kv-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.kv-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.kv-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.kv-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 →