Delete a single document from a collection
AI agents call deleteOne to permanently remove resources in MongoDB MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
deleteOne irreversibly removes data from the database with no built-in undo mechanism. Even though it only affects a single document rather than many or an entire collection, the destructive nature and irreversibility of the operation places it in the Destructive category with high severity.
From the tool's definition deleteOne performs an irreversible delete operation on a single document in MongoDB. The description explicitly states 'Delete a single document from a collection', and the tool name contains 'delete' which is a canonical destructive action.
Attacks that exploit this kind of access
Delete a single document from a collection. It is categorised as a Destructive tool in the MongoDB MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MongoDB MCP Server MCP server in PolicyLayer and add a rule for deleteOne: 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 MongoDB MCP Server. Nothing to install.
deleteOne 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 deleteOne 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 deleteOne. 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.
deleteOne is provided by the MongoDB MCP Server MCP server (ryaker/mongodb-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 →