How to Use the Milvus (Open-Source Vector Database) MCP in LangChain

Q: How does LangChain use the Milvus (Open-Source Vector Database) MCP Server for hybrid search?

Your LangChain agent combines searchvectors for semantic similarity with queryentities for scalar filtering. The agent analyzes the results of the vector search, writes a logical filter, and runs a follow-up query to pinpoint the exact records you need.

Q: Can a LangChain agent discover available collections in Milvus (Open-Source Vector Database) dynamically?

Yes, the agent calls listcollections first to map out what is available in your database. From there, it can run describecollection to understand the schema of a specific target before executing any vector searches.

Q: What happens if my LangChain agent tries to search an empty Milvus (Open-Source Vector Database) collection?

The agent can run getcollectionstats to check the current row count before initiating a heavy search. If the collection is empty, the LangChain loop can gracefully bypass the searchvectors step to save latency.

Q: How do I handle batch deletions in LangChain?

You pass the target primary keys through your chain to the deleteentities tool. The agent can first run getentities to double-check the payloads, ensuring it only deletes the exact records your chain flagged.

Build LangChain chains that run ANN vector searches and manage Milvus collections via this MCP server.

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 LangChain

Create your Vinkius account to connect Milvus (Open-Source Vector Database) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let your LangChain agents search Milvus vectors directly

The `search_vectors` tool lets your LangChain agent run fast similarity lookups by dumping raw embedding arrays straight into your Milvus collections. This isn't some basic search. It's a dynamic step in a ReAct loop where the agent reads the output to figure out what to fetch next. If the vector search returns garbage confidence scores, the agent pivots on the spot. It uses `query_entities` to apply scalar filters or falls back to a broader lookup, keeping your chain moving without manual intervention.

Inspect and manage collection schemas in any chain

The `describe_collection` tool exposes the exact schema definitions and index configurations of your Milvus setup to your LangChain pipeline. Your agent reads this structure to understand what fields are available before formatting complex scalar queries. To avoid blowing up on empty collections, the agent can call `get_collection_stats` to check row counts first. This keeps your LangChain run from crashing when dealing with newly initialized or cold vector stores.

Multi-step cleanups using the Milvus MCP Server

The `delete_entities` tool gives your LangChain agent the keys to prune stale vectors using their primary keys. When an agent identifies outdated records during a processing chain, it targets them for removal instantly. Before pulling the trigger, the agent uses `get_entities` to inspect the exact payload first. This safety loop ensures your LangChain workflow only deletes the precise records you intended to drop.

Setup guide

Set up Milvus (Open-Source Vector Database) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Milvus (Open-Source Vector Database) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "milvus-open-source-vector-database-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Milvus (Open-Source Vector Database) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your LangChain agent combines `search_vectors` for semantic similarity with `query_entities` for scalar filtering. The agent analyzes the results of the vector search, writes a logical filter, and runs a follow-up query to pinpoint the exact records you need.

Yes, the agent calls `list_collections` first to map out what is available in your database. From there, it can run `describe_collection` to understand the schema of a specific target before executing any vector searches.

The agent can run `get_collection_stats` to check the current row count before initiating a heavy search. If the collection is empty, the LangChain loop can gracefully bypass the `search_vectors` step to save latency.

You pass the target primary keys through your chain to the `delete_entities` tool. The agent can first run `get_entities` to double-check the payloads, ensuring it only deletes the exact records your chain flagged.

Your raw vector arrays, primary keys, and schema metadata are processed within an ephemeral, zero-trust V8 isolate. Vinkius never stores your vector payloads or collection schemas, keeping your proprietary database queries completely isolated.

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