AI agents use insert_entities to create or update resources in Zilliz MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zilliz MCP Server environment.
The insert_entities tool creates or adds new records to a vector database collection. This is a reversible write operation (data can be updated or deleted later via other tools like delete_entities). While the description field is empty, the tool name and server context clearly establish this as a Write category action.
From the tool's definition Tool name 'insert_entities' combined with server context describing 'insert vector data' indicates data creation/modification operations. Server description explicitly mentions 'insert vector data' as a capability.
Documented attack patterns abuse exactly the kind of access insert_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 insert_entities:
{
"version": "1",
"default": "deny",
"tools": {
"insert_entities": {
"limits": [
{
"counter": "insert_entities_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}insert_entities stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
insert_entities. It is categorised as a Write tool in the Zilliz MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zilliz MCP Server MCP server in PolicyLayer and add a rule for insert_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.
insert_entities is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the insert_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 insert_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.
insert_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.