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

Q: Can I combine Milvus (Open-Source Vector Database) with Google ADK for RAG pipelines?

Yes. Your Gemini model uses searchvectors to pull relevant context, then processes that context using its 1M token window. This lets you build high-capacity retrieval systems on Google Cloud.

Q: How do I restrict tool access for Milvus (Open-Source Vector Database) in Google ADK?

You pass a list of allowed tool names to the McpToolset constructor. For example, you can expose searchvectors and block deleteentities to keep your database safe.

Connect Gemini's 1M token context to Milvus (Open-Source Vector Database) using Google ADK with this dedicated 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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run semantic searches with Google ADK

This MCP Server exposes `search_vectors` to let Gemini search millions of embedded records directly from your enterprise cloud environment. The model processes massive context windows and extracts precise vector coordinates to query the database. Google ADK handles the transport layer directly by wrapping the HTTP server inside an `McpToolset`. This setup allows your agents to cross-reference search results with structured datasets sitting in BigQuery.

Query scalar metadata and collection schemas

Run `query_entities` to filter your vector database using SQL-like scalar expressions. Your Gemini agent uses this MCP tool to narrow down millions of documents to a specific customer ID before running similarity searches. To understand the underlying data structure, the agent calls `describe_collection` to inspect schema definitions and index types. This prevents the model from generating malformed queries that violate field constraints.

Track database health and clean up stale vectors

Run `get_collection_stats` to fetch live row counts and memory usage from your cluster. Your Google ADK agent monitors these metrics to decide when to trigger background indexing or optimization routines. When documents are updated, the agent calls `delete_entities` using primary keys to purge outdated coordinate records. You can restrict which tools are exposed by passing a filtered list to the agent initialization block.

Setup guide

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

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Milvus (Open-Source Vector Database) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Milvus (Open-Source Vector Database)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Milvus (Open-Source Vector Database) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Yes. Your Gemini model uses `search_vectors` to pull relevant context, then processes that context using its 1M token window. This lets you build high-capacity retrieval systems on Google Cloud.

You pass a list of allowed tool names to the `McpToolset` constructor. For example, you can expose `search_vectors` and block `delete_entities` to keep your database safe.

The Vinkius MCP Server manages HTTP connection pooling to handle concurrent requests. Your agent can execute parallel calls to `query_entities` without bottlenecking the database.

Yes, as long as your local runtime can access the Vinkius endpoint. The ADK connects over standard HTTP or Stdio transports to communicate with the database tools.

Your vector embeddings and primary key fields are processed inside an ephemeral, zero-trust MCP container. The credentials used to connect to your database instance are fully encrypted and never exposed to the LLM.

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