milvus-multi-vector-search

THE RISK

Low Risk

Why milvus-multi-vector-search needs a policy

Vector similarity search retrieves data based on similarity matching without altering, deleting, or creating data. It is a non-destructive query operation analogous to SELECT in SQL. The tool fits the Read category definition: 'retrieves or queries data; no side effects'. Severity is low because misuse (e.g., searching for unintended vector matches) has no blast radius beyond information disclosure.

From the tool's definition Tool name and description indicate 'search' operation: 'Perform vector similarity search with multiple query vectors'. Search is a read-only query operation with no data modification, deletion, or code execution.

Documented attack patterns abuse exactly the kind of access milvus-multi-vector-search gives an agent:

POLICY

How to control milvus-multi-vector-search

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-multi-vector-search:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "milvus-multi-vector-search": {}
  }
}

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

Create a free account and register Milvus MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Milvus MCP Server tools

Destructive milvus-delete-entities Delete entities from a collection based on filter expression Execute milvus-load-collection Load a collection into memory for search and query Execute milvus-release-collection Release a collection from memory Write milvus-bulk-insert Insert data in batches for better performance Write milvus-create-collection Create a new collection with specified schema Write milvus-create-dynamic-field Add a dynamic field to an existing collection Write milvus-create-index Create an index on a vector field Write milvus-insert-data Insert data into a collection

All 21 Milvus MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about milvus-multi-vector-search

What does the milvus-multi-vector-search tool do? +

Perform vector similarity search with multiple query vectors. It is categorised as a Read tool in the Milvus MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on milvus-multi-vector-search? +

Register the Milvus MCP Server MCP server in PolicyLayer and add a rule for milvus-multi-vector-search: 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.

What risk level is milvus-multi-vector-search? +

milvus-multi-vector-search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit milvus-multi-vector-search? +

Yes. Add a rate_limit block to the milvus-multi-vector-search 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 milvus-multi-vector-search completely? +

Set action: deny in the PolicyLayer policy for milvus-multi-vector-search. 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 milvus-multi-vector-search? +

milvus-multi-vector-search 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.

Enforce policy on every Milvus MCP Server tool call.

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.

CHECK YOUR STACK →