AI agents call describe_cluster to retrieve information from Zilliz MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The describe_cluster tool retrieves and returns information about a cluster's properties and status. This is a read operation with no side effects—it does not create, modify, delete, or execute code. Even in the absence of a detailed description, the naming pattern matches other Read-category tools on this server (describe_collection, list_clusters, list_databases, list_projects).
From the tool's definition Tool name 'describe_cluster' and server context indicate retrieval of cluster metadata/configuration. No description provided, but naming convention aligns with read-only operations like 'describe_collection' and 'list_clusters' on the same server.
Documented attack patterns abuse exactly the kind of access describe_cluster 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 describe_cluster:
{
"version": "1",
"default": "deny",
"tools": {
"describe_cluster": {}
}
}describe_cluster is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
describe_cluster. It is categorised as a Read tool in the Zilliz MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zilliz MCP Server MCP server in PolicyLayer and add a rule for describe_cluster: 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.
describe_cluster is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the describe_cluster 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 describe_cluster. 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.
describe_cluster 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.