Critical Risk →

drop_object

Drop a Snowflake database object permanently

Risk signalsDestroys database/schema/table

Part of the Snowflake server.

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

SECURE SNOWFLAKE →

Free to start. No card required.

AI agents may call drop_object to permanently remove or destroy resources in Snowflake. 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 drop_object in a loop, permanently destroying resources in Snowflake. 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": [
    "drop_object"
  ]
}

See the full Snowflake policy for all 10 tools.

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

ENFORCE ON MY SNOWFLAKE →

View all 10 tools →

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

SECURE SNOWFLAKE →

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

What does the drop_object tool do? +

Drop a Snowflake database object permanently. It is categorised as a Destructive tool in the Snowflake 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 drop_object? +

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

What risk level is drop_object? +

drop_object 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 drop_object? +

Yes. Add a rate_limit block to the drop_object 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 drop_object completely? +

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

drop_object is provided by the Snowflake MCP server (@snowflake-labs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Snowflake tool call.

Deterministic rules across all 10 Snowflake 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.