AI agents call delete_draft to permanently remove resources in Substack — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data (a draft post) with no recovery mechanism. The explicit warning that it 'cannot be undone' confirms it is a destructive action. Severity is 'high' rather than 'critical' because the blast radius is limited to draft content on one publication, not production posts or financial systems, though an AI agent misusing this could still cause significant user frustration by removing…
From the tool's definition Tool description explicitly states 'Permanently delete' and 'This cannot be undone.' Tool name uses 'delete' which is a destructive operation.
Documented attack patterns abuse exactly the kind of access delete_draft gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Substack, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_draft:
{
"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.
Free to start. No card required.
Permanently delete a draft. This cannot be undone. It is categorised as a Destructive tool in the Substack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Substack 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. Nothing to install.
delete_draft 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_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.
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.
delete_draft is provided by the Substack MCP server (nanameru/substack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Substack, 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.
11 Substack tools catalogued and risk-classified — across an index of 43,000+ MCP servers.