Drop all indexed pages from the active session.
AI agents call clear to permanently remove resources in Nesift — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes all indexed pages without opportunity for recovery within the session context. While the blast radius is scoped to the active session (mitigating somewhat), the irreversible deletion of potentially significant indexed content and the loss of work/data justifies Destructive classification.
From the tool's definition Tool description explicitly states "Drop all indexed pages from the active session" — the verb "drop" combined with "all" indicates irreversible deletion of all indexed content in the session.
Attacks that exploit this kind of access
Drop all indexed pages from the active session. It is categorised as a Destructive tool in the Nesift MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nesift MCP server in PolicyLayer and add a rule for clear: 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 Nesift. Nothing to install.
clear 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 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. 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 is provided by the Nesift MCP server (scottgl9/nesift). 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 →