AI agents call drop_collection to permanently remove resources in Codehooks Io MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Dropping a collection permanently removes all data within it and cannot be undone. This is an irreversible destructive action affecting potentially large datasets, warranting the Destructive category and high severity. The confidence is high because the intent is explicit and unambiguous.
From the tool's definition Tool name is 'drop_collection' and description states 'Delete a collection'. The verb 'delete' and the action of dropping an entire collection indicate irreversible removal of data.
Documented attack patterns abuse exactly the kind of access drop_collection gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codehooks Io MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for drop_collection:
{
"version": "1",
"default": "deny",
"hide": [
"drop_collection"
]
}drop_collection 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.
Delete a collection. It is categorised as a Destructive tool in the Codehooks Io MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Codehooks Io MCP Server MCP server in PolicyLayer and add a rule for drop_collection: 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 Codehooks Io MCP Server. Nothing to install.
drop_collection 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 drop_collection 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 drop_collection. 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.
drop_collection is provided by the Codehooks Io MCP Server MCP server (restdb/codehooks-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codehooks Io MCP Server, 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.
20 Codehooks Io MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.