Delete a slide from a presentation
AI agents call delete_slide to permanently remove resources in Makeslates — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a slide from a presentation, which cannot be undone. Although the blast radius is somewhat limited (one slide rather than an entire presentation), deletion operations are irreversible and qualify as Destructive. The severity is high because an AI agent could accidentally remove important slides from a user's presentation, causing data loss.
From the tool's definition Tool name: 'delete_slide'. Description: 'Delete a slide from a presentation'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a slide from a presentation. It is categorised as a Destructive tool in the Makeslates MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Makeslates MCP server in PolicyLayer and add a rule for delete_slide: 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 Makeslates. Nothing to install.
delete_slide 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_slide 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_slide. 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_slide is provided by the Makeslates MCP server (makeslates-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 →