Low Risk

describe_collection

describe_collection

How to control describe_collection ↓

AI agents call describe_collection 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.

Low Risk

The 'describe_collection' operation retrieves metadata or schema information about a Milvus collection. This is a non-destructive query operation that returns information without modifying state. While the description is empty, the semantics of 'describe' as a command—combined with sibling read operations on this server—confirm this is a Read category tool.

From the tool's definition Tool name 'describe_collection' follows standard read-only operation naming patterns (describe, list, get). Sibling tools include 'list_clusters', 'list_collections', 'describe_cluster' which are all Read operations.

Documented attack patterns abuse exactly the kind of access describe_collection 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_collection:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "describe_collection": {}
  }
}

describe_collection is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Zilliz MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the describe_collection tool do? +

describe_collection. It is categorised as a Read tool in the Zilliz MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on describe_collection? +

Register the Zilliz MCP Server MCP server in PolicyLayer and add a rule for describe_collection: 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.

What risk level is describe_collection? +

describe_collection is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit describe_collection? +

Yes. Add a rate_limit block to the describe_collection 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.

How do I block describe_collection completely? +

Set action: deny in the PolicyLayer policy for describe_collection. 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.

What MCP server provides describe_collection? +

describe_collection 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.

Enforce policy on every Zilliz MCP Server tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.