AI agents call delete_entities to permanently remove resources in Zilliz MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of database entities is irreversible and constitutes a destructive operation. While the description is empty (lowering confidence slightly from 0.98 to 0.95), the tool name unambiguously indicates data destruction. The blast radius is high because an AI agent could permanently remove vector data collections without proper safeguards.
From the tool's definition Tool name is 'delete_entities' which directly indicates deletion/removal of data from a vector database. The server context confirms this operates on Milvus collections where entities represent stored vector data.
Documented attack patterns abuse exactly the kind of access delete_entities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zilliz MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_entities:
{
"version": "1",
"default": "deny",
"hide": [
"delete_entities"
]
}delete_entities 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_entities. It is categorised as a Destructive tool in the Zilliz MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zilliz MCP Server MCP server in PolicyLayer and add a rule for delete_entities: 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 Zilliz MCP Server. Nothing to install.
delete_entities 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_entities 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_entities. 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_entities is provided by the Zilliz MCP Server MCP server (zilliztech/zilliz-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Zilliz MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 Zilliz MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.