清除 scroll 查询上下文，释放资源
AI agents call clear_scroll to permanently remove resources in Elasticsearch MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool clears/destroys an active scroll context in Elasticsearch. While it doesn't delete data, it irreversibly terminates a scroll session and releases server-side resources associated with it. This is an action that cannot be undone — once the scroll context is cleared, any ongoing pagination using that scroll ID is permanently invalidated.
From the tool's definition 清除 scroll 查询上下文，释放资源 (Clear scroll query context, release resources)
Attacks that exploit this kind of access
清除 scroll 查询上下文，释放资源. It is categorised as a Destructive tool in the Elasticsearch MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Elasticsearch MCP Server MCP server in PolicyLayer and add a rule for clear_scroll: 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 Elasticsearch MCP Server. Nothing to install.
clear_scroll 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_scroll 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_scroll. 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_scroll is provided by the Elasticsearch MCP Server MCP server (macgaf/es_mcp_server). 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 →