Delete entities from a collection based on filter expression
AI agents call milvus-delete-entities to permanently remove resources in Milvus 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 Milvus vector database collection. Deletion is an irreversible operation that cannot be undone. While the filter expression provides some guardrail against accidental deletion of entire collections, a malicious or careless AI agent could still cause significant data loss by crafting a broad filter or deleting critical entities.
From the tool's definition Tool name contains 'delete' and description states 'Delete entities from a collection based on filter expression'. The delete operation on database entities is irreversible.
Documented attack patterns abuse exactly the kind of access milvus-delete-entities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Milvus MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for milvus-delete-entities:
{
"version": "1",
"default": "deny",
"hide": [
"milvus-delete-entities"
]
} milvus-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 from a collection based on filter expression. It is categorised as a Destructive tool in the Milvus MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Milvus MCP Server MCP server in PolicyLayer and add a rule for milvus-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 Milvus MCP Server. Nothing to install.
milvus-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 milvus-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 milvus-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.
milvus-delete-entities is provided by the Milvus MCP Server MCP server (stephen37/mcp-server-milvus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Milvus MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Milvus MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.