Critical Risk →

delete_resource

Permanently delete one of the caller's resources. Drops the underlying Postgres database (or clears the webhook's request log), then marks the row status='deleted'. Paid tier only. Free-tier resources auto-expire in 24h and cannot be deleted manually — the tool will surface the upgrade URL. Requi...

Risk signalsHandles credentials or secrets (token)

Part of the Instanode server.

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

SECURE INSTANODE →

Free to start. No card required.

AI agents may call delete_resource to permanently remove or destroy resources in Instanode. 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_resource in a loop, permanently destroying resources in Instanode. 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_resource"
  ]
}

See the full Instanode policy for all 6 tools.

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

ENFORCE ON MY INSTANODE →

These attack patterns abuse exactly the kind of access delete_resource 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_resource only ever does what you allow.

SECURE INSTANODE →

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

What does the delete_resource tool do? +

Permanently delete one of the caller's resources. Drops the underlying Postgres database (or clears the webhook's request log), then marks the row status='deleted'. Paid tier only. Free-tier resources auto-expire in 24h and cannot be deleted manually — the tool will surface the upgrade URL. Requires INSTANODE_TOKEN.. It is categorised as a Destructive tool in the Instanode 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_resource? +

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

What risk level is delete_resource? +

delete_resource 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_resource? +

Yes. Add a rate_limit block to the delete_resource 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_resource completely? +

Set action: deny in the PolicyLayer policy for delete_resource. 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_resource? +

delete_resource is provided by the Instanode MCP server (@instanode/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Instanode tool call.

Deterministic rules across all 6 Instanode 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.