Drop a collection and its indexes from a database
AI agents call drop-collection to permanently remove resources in Mongodb3 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion of an entire collection and its indexes. This cannot be undone and represents permanent data loss. Destructive category is the most severe applicable, and the severity is critical due to the potential for complete loss of a database collection's data.
From the tool's definition Tool name is 'drop-collection' and description states 'Drop a collection and its indexes from a database'—dropping a collection irreversibly deletes all data and associated indexes.
Attacks that exploit this kind of access
Drop a collection and its indexes from a database. It is categorised as a Destructive tool in the Mongodb3 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mongodb3 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 Mongodb3. 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 Mongodb3 MCP server (mongodb3-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →