ページを削除。SCRAPBOX_ENABLE_DELETE=true が必要。この操作は取り消せません。
AI agents call delete_page to permanently remove resources in MCP Template — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (a page from what appears to be a Scrapbox-like system). The description explicitly states the operation cannot be undone, and the presence of a feature flag to enable deletion indicates it is recognized as a dangerous action. This is a clear case of Destructive category—the most severe category applicable.
From the tool's definition Tool description states 'ページを削除' (delete page) and explicitly warns '取り消せません' (cannot be undone). The requirement for SCRAPBOX_ENABLE_DELETE=true flag further confirms this is a guarded destructive operation.
Attacks that exploit this kind of access
ページを削除。SCRAPBOX_ENABLE_DELETE=true が必要。この操作は取り消せません。. It is categorised as a Destructive tool in the MCP Template MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Template MCP server in PolicyLayer and add a rule for delete_page: 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 Template. Nothing to install.
delete_page 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 delete_page 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 delete_page. 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.
delete_page is provided by the MCP Template MCP server (masseater/scrapbox-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 →