How to Use the Milvus (Open-Source Vector Database) MCP in OpenAI Agents SDK

Q: How does Milvus (Open-Source Vector Database) handle tool discovery in OpenAI Agents SDK?

The SDK automatically maps the database tools like listcollections and searchvectors directly to your agent's execution context. You just pass the HTTP server URL during initialization, and the agents discover the capabilities on boot.

Q: Can I run hybrid searches using Milvus (Open-Source Vector Database) and OpenAI Agents SDK?

Yes. Your agent runs queryentities to filter by scalar attributes, then feeds those filtered IDs into searchvectors for the final similarity check. The SDK handles this multi-step reasoning natively.

Q: How does caching work with these tools?

You set cacheToolsList=True in your Python agent configuration to avoid fetching the tool definitions on every turn. This keeps latency low when querying collections.

Run production-grade vector search pipelines using this MCP Server inside OpenAI Agents SDK with strict agent guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

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

Create your Vinkius account to connect Milvus (Open-Source Vector Database) to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Milvus (Open-Source Vector Database) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute vector searches with OpenAI Agents SDK

This MCP Server exposes `search_vectors` to query your high-dimensional coordinates directly from your agentic workflows. Your agent converts natural language queries into raw vector arrays, feeds them to the database, and gets the closest matches back. The OpenAI Agents SDK automatically registers this tool when you boot up the streamable HTTP server. Your specialized agents can hand off search tasks to each other while the OpenAI dashboard traces every single query vector payload.

Inspect and manage collections on the fly

Run `list_collections` to discover what vector tables are available for your agent to target. Before executing heavy queries, your agent uses `describe_collection` to check the exact schema layout and index parameters. Monitoring storage limits is straightforward with `get_collection_stats` which returns real-time row counts. This MCP setup prevents your OpenAI Agents SDK pipeline from hitting hard memory limits or querying empty vector spaces.

Modify and clean up vector entities safely

Use `delete_entities` to remove specific vector records using their primary keys when users delete their accounts or update their profiles. You can also fetch specific entries using `get_entities` to confirm the deletion worked. For complex filtering, your agent invokes `query_entities` with scalar expressions to narrow down the search space before running a full vector sweep. The OpenAI Agents SDK applies built-in guardrails to make sure these mutations happen only under authorized conditions.

Setup guide

Set up Milvus (Open-Source Vector Database) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Milvus (Open-Source Vector Database) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Milvus (Open-Source Vector Database) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Milvus (Open-Source Vector Database) tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Milvus (Open-Source Vector Database) Agent",
            instructions="You have access to Milvus (Open-Source Vector Database) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Milvus. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Milvus (Open-Source Vector Database) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Milvus (Open-Source Vector Database) MCP in OpenAI Agents SDK

The SDK automatically maps the database tools like `list_collections` and `search_vectors` directly to your agent's execution context. You just pass the HTTP server URL during initialization, and the agents discover the capabilities on boot.

Yes. Your agent runs `query_entities` to filter by scalar attributes, then feeds those filtered IDs into `search_vectors` for the final similarity check. The SDK handles this multi-step reasoning natively.

The MCP Server lets you apply strict execution guardrails before the agent calls `delete_entities`. This prevents unauthorized deletion of your vector records.

You set `cacheToolsList=True` in your Python agent configuration to avoid fetching the tool definitions on every turn. This keeps latency low when querying collections.

All vector embeddings and primary keys stay inside your isolated V8 sandbox on Vinkius. The MCP Server communicates over encrypted HTTP streams, so your raw coordinate data never leaks to unauthorized external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript