Critical Risk →

delete_draft

Delete a draft post. IMPORTANT: You MUST ALWAYS ask the user to confirm deletion in a follow-up message BEFORE calling this tool with confirm_delete=true. Never set confirm_delete=true on the first request, even if the user explicitly asks to delete. This ensures users have time to reconsider thi...

How to control delete_draft ↓

What delete_draft does on Substack Mcp Plus

AI agents call delete_draft to permanently remove resources in Substack Mcp Plus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why delete_draft needs a policy

This tool permanently deletes draft posts with no undo capability. While the blast radius is somewhat limited to draft content (not published posts), deletion is irreversible and represents clear data destruction. The tool's own documentation emphasizes the permanence ('permanent action'), confirming the Destructive category.

From the tool's definition Tool name is 'delete_draft' and description states 'Delete a draft post' and 'this permanent action', indicating irreversible deletion of data.

Documented attack patterns abuse exactly the kind of access delete_draft gives an agent:

How to control delete_draft

PolicyLayer is an MCP gateway — it sits between your AI agents and Substack Mcp Plus, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_draft:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_draft"
  ]
}

delete_draft disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Substack Mcp Plus — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about delete_draft

What does the delete_draft tool do? +

Delete a draft post. IMPORTANT: You MUST ALWAYS ask the user to confirm deletion in a follow-up message BEFORE calling this tool with confirm_delete=true. Never set confirm_delete=true on the first request, even if the user explicitly asks to delete. This ensures users have time to reconsider this permanent action. It is categorised as a Destructive tool in the Substack Mcp Plus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_draft? +

Register the Substack Mcp Plus MCP server in PolicyLayer and add a rule for delete_draft: 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 Substack Mcp Plus. Nothing to install.

What risk level is delete_draft? +

delete_draft is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_draft? +

Yes. Add a rate_limit block to the delete_draft 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.

How do I block delete_draft completely? +

Set action: deny in the PolicyLayer policy for delete_draft. 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.

What MCP server provides delete_draft? +

delete_draft is provided by the Substack Mcp Plus MCP server (ty13r/substack-mcp-plus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Substack Mcp Plus tool call.

Start from Substack Mcp Plus, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

12 Substack Mcp Plus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.