Query collection using filter expressions. Args: collection_name: Name of the collection to query filter_expr: Filter expression (e.g. 'age > 20') output_fields: Fields to include in results limit: Maximum number of results
AI agents call milvus_query to retrieve information from MCP Server for Milvus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
milvus_query retrieves data from a Milvus collection based on filter criteria and returns results. This is a read operation with no irreversible changes to data. It matches the 'Read' category definition: retrieves or queries data with no side effects. The low severity reflects that querying a vector database carries minimal risk of misuse—the blast radius is confined to information disclosure of existing data.
From the tool's definition Tool performs 'Query collection using filter expressions' with parameters for filtering and retrieving results (collection_name, filter_expr, output_fields, limit).
Documented attack patterns abuse exactly the kind of access milvus_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server for Milvus, and nothing reaches the server without passing your rules. This is the rule we recommend for milvus_query:
{
"version": "1",
"default": "deny",
"tools": {
"milvus_query": {}
}
}milvus_query 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.
Query collection using filter expressions. Args: collection_name: Name of the collection to query filter_expr: Filter expression (e.g. 'age > 20') output_fields: Fields to include in results limit: Maximum number of results. It is categorised as a Read tool in the MCP Server for Milvus MCP Server, which means it retrieves data without modifying state.
Register the MCP Server for Milvus MCP server in PolicyLayer and add a rule for milvus_query: 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 MCP Server for Milvus. Nothing to install.
milvus_query 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_query 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_query. 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_query is provided by the MCP Server for Milvus MCP server (zilliztech/mcp-server-milvus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 MCP Server for Milvus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 MCP Server for Milvus tools catalogued and risk-classified — across an index of 42,500+ MCP servers.