Remove an inbox item by matching text.
AI agents call clear_inbox_item_tool to permanently remove resources in Alaya — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs deletion of inbox items without indication of recovery or undo capability. While the blast radius is limited to inbox items rather than the entire vault, deletion is inherently destructive and irreversible. This is more severe than Write (which is reversible) but less severe than if it deleted entire notes or the knowledge base itself.
From the tool's definition Tool description states 'Remove an inbox item' which indicates deletion/removal of data. The tool name contains 'clear' which typically implies erasure.
Attacks that exploit this kind of access
Remove an inbox item by matching text. It is categorised as a Destructive tool in the Alaya MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Alaya MCP server in PolicyLayer and add a rule for clear_inbox_item_tool: 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 Alaya. Nothing to install.
clear_inbox_item_tool 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 clear_inbox_item_tool 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 clear_inbox_item_tool. 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.
clear_inbox_item_tool is provided by the Alaya MCP server (luke-kucing/alaya). 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 →