Critical Risk →

delete_website

Permanently delete a published website. The site will be immediately inaccessible. Requires authentication via edit_key or api_key, and requires confirm: true as a safety mechanism to prevent accidental deletion. Use this when a user explicitly asks you to remove or delete a site. IMPORTANT: Alwa...

Risk signalsHandles credentials or secrets (api_key)

Part of the YeetIt server.

delete_website can permanently delete data in YeetIt, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE YEETIT →

Free to start. No card required.

AI agents may call delete_website to permanently remove or destroy resources in YeetIt. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call delete_website in a loop, permanently destroying resources in YeetIt. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

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

See the full YeetIt policy for all 4 tools.

Get this rule live on your own YeetIt server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY YEETIT →

These attack patterns abuse exactly the kind of access delete_website gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so delete_website only ever does what you allow.

SECURE YEETIT →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the delete_website tool do? +

Permanently delete a published website. The site will be immediately inaccessible. Requires authentication via edit_key or api_key, and requires confirm: true as a safety mechanism to prevent accidental deletion. Use this when a user explicitly asks you to remove or delete a site. IMPORTANT: Always confirm with the user before calling this tool — deletion cannot be undone.. It is categorised as a Destructive tool in the YeetIt 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_website? +

Register the YeetIt MCP server in PolicyLayer and add a rule for delete_website: 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 YeetIt. Nothing to install.

What risk level is delete_website? +

delete_website 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_website? +

Yes. Add a rate_limit block to the delete_website 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_website completely? +

Set action: deny in the PolicyLayer policy for delete_website. 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_website? +

delete_website is provided by the YeetIt MCP server (https://yeetit.site/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every YeetIt tool call.

Deterministic rules across all 4 YeetIt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.