Perform vector similarity search on a collection
AI agents call milvus-vector-search to retrieve information from Milvus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Vector search is a read-only operation that queries a collection to find similar vectors based on similarity metrics. It returns results without creating, modifying, deleting, or executing arbitrary operations. No side effects or data mutations occur. The low severity reflects minimal blast radius even if misused—an agent might retrieve unintended data, but no destructive or irreversible operations are possible.
From the tool's definition Tool name 'milvus-vector-search' and description 'Perform vector similarity search on a collection' indicate a query operation that retrieves matching vectors without modifying data.
Documented attack patterns abuse exactly the kind of access milvus-vector-search 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-vector-search:
{
"version": "1",
"default": "deny",
"tools": {
"milvus-vector-search": {}
}
} milvus-vector-search 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.
Perform vector similarity search on a collection. It is categorised as a Read tool in the Milvus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Milvus MCP Server MCP server in PolicyLayer and add a rule for milvus-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.
milvus-vector-search 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 milvus-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.
Set action: deny in the PolicyLayer policy for milvus-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.
milvus-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.
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.