Delete points from a collection
AI agents call delete_points to permanently remove resources in Qdrant 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 data from the Qdrant vector database. Deletion of data points cannot be undone and represents loss of information. While not a financial transaction, the irreversible nature of data deletion makes this Destructive rather than Write.
From the tool's definition Tool name is 'delete_points' with description 'Delete points from a collection'. The verb 'delete' combined with operation on stored data points indicates irreversible removal.
Attacks that exploit this kind of access
Delete points from a collection. It is categorised as a Destructive tool in the Qdrant MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qdrant MCP Server MCP server in PolicyLayer and add a rule for delete_points: 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 Qdrant MCP Server. Nothing to install.
delete_points 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_points 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_points. 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_points is provided by the Qdrant MCP Server MCP server (jimmy974/qdrant-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 →