How do I perform an ANN search through my agent?

Use the `search_vectors` tool by providing the collection name and a JSON float array matching the collection's dimensions. Your agent will perform an Approximate Nearest Neighbor search and return the most semantically relevant entities.

Can I filter results using structured fields instead of just vectors?

Yes. Use the `query_entities` tool with a Milvus-style filter expression. This allows you to retrieve entities based on primary keys, tags, or other scalar fields without necessarily performing a vector similarity search.

How do I check the schema and dimension requirements for a Milvus collection?

The `describe_collection` tool retrieves the complete schema mapping. Your agent will report the required vector dimensions, index types, and primary key names, helping you ensure your search queries are compatible with the database logic.

Milvus (Open-Source Vector Database) MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: Milvus (Open-Source Vector Database)
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Milvus (Open-Source Vector Database) through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Milvus (Open-Source Vector Database) Assistant",
            instructions=(
                "You help users interact with Milvus (Open-Source Vector Database). "
                "You have access to 7 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Milvus (Open-Source Vector Database)"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Milvus (Open-Source Vector Database) MCP Server

Connect your Milvus instance to any AI agent and take full control of your high-performance vector search, embedding storage, and scalar data management through natural conversation.

The OpenAI Agents SDK auto-discovers all 7 tools from Milvus (Open-Source Vector Database) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Milvus (Open-Source Vector Database), another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Vector Search Orchestration — Execute Approximate Nearest Neighbor (ANN) searches against your collections by providing raw embedding vectors to retrieve semantically relevant matches directly from your agent
Scalar Query Filters — Use sophisticated scalar expressions to filter entities by structured fields (e.g., tags, IDs, dates) alongside your vector search for precise data retrieval
Collection Lifecycle Audit — List all managed vector collections and retrieve detailed schema definitions, including dimensions, primary keys, and index types natively
Performance Statistics — Extract real-time metrics for your collections, including entity counts and physical memory usage, to monitor the health of your vector store
Precision Retrieval — Fetch specific vector items by their primary keys, bypassing standard semantic boundaries to audit exact data points securely
Data Management — Irreversibly delete specific vector records using primary identifiers to maintain a clean and optimized search index across your Milvus instance

The Milvus (Open-Source Vector Database) MCP Server exposes 7 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Milvus (Open-Source Vector Database) to OpenAI Agents SDK via MCP

Follow these steps to integrate the Milvus (Open-Source Vector Database) MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 7 tools from Milvus (Open-Source Vector Database)

Why Use OpenAI Agents SDK with the Milvus (Open-Source Vector Database) MCP Server

OpenAI Agents SDK provides unique advantages when paired with Milvus (Open-Source Vector Database) through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Milvus (Open-Source Vector Database) + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Milvus (Open-Source Vector Database) MCP Server delivers measurable value.

Automated workflows: build agents that query Milvus (Open-Source Vector Database), process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Milvus (Open-Source Vector Database), another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Milvus (Open-Source Vector Database) tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Milvus (Open-Source Vector Database) to resolve tickets, look up records, and update statuses without human intervention

Milvus (Open-Source Vector Database) MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect Milvus (Open-Source Vector Database) to OpenAI Agents SDK via MCP:

delete_entities

Irreversibly delete specific vector records utilizing primary keys

describe_collection

Explore the explicit schema mapping and indexing definition of a Milvus collection

get_collection_stats

Get collection statistics bounding row counts natively

get_entities

Extract unique vector items bounding exactly by known Primary Keys

list_collections

Always query this first. List index collections tracked inside the Milvus Vector Database

query_entities

Query explicitly using scalar expressions to retrieve entities

search_vectors

Make sure to feed a strict explicit JSON Array matching exact dimensions. Search nearest vector neighbors matching implicit embedding inputs

Example Prompts for Milvus (Open-Source Vector Database) in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Milvus (Open-Source Vector Database) immediately.

"List all vector collections in my Milvus instance"

"Search collection 'text_knowledge_base' for vector: [0.1, -0.2, ...]"

"Show me the row count and memory stats for collection 'image_embeddings'"

Troubleshooting Milvus (Open-Source Vector Database) MCP Server with OpenAI Agents SDK

Common issues when connecting Milvus (Open-Source Vector Database) to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Milvus (Open-Source Vector Database) + OpenAI Agents SDK FAQ

Common questions about integrating Milvus (Open-Source Vector Database) MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.