从指定集合中删除文档
AI agents call delete 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.
This tool permanently removes documents from a database without possibility of recovery through the tool itself. While severity is high rather than critical (depends on data scope and backup existence), it is classified as Destructive because deletion operations cannot be undone and represent the most severe category applicable. An AI agent misusing this could cause significant data loss.
From the tool's definition Tool name 'delete' and description '从指定集合中删除文档' (delete documents from specified collection) indicate irreversible removal of data from MongoDB collections.
Attacks that exploit this kind of access
从指定集合中删除文档. 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 delete: 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.
delete 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 delete 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 delete. 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.
delete is provided by the MongoDB MCP Server MCP server (linpeibiao/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 →