How to Use the Vertex AI Vector Search MCP in Google ADK

Q: How do I use Vertex AI Vector Search with Google ADK?

Your agent invokes searchnearestneighbors when it needs contextual answers. It sends the required endpoint ID, index ID, and query vector to find the closest matches in your embeddings.

Q: Can I use Vertex AI Vector Search with Google ADK to list all available indexes?

Yes. The listvectorindexes tool allows your agent to pull a comprehensive list of every vector index in the project, making discovery seamless for your enterprise workflow.

Q: Does Vertex AI Vector Search support tracking operations when using Google ADK?

It does. The listvectoroperations tool allows your agent to check on long-running processes—like index creation or updates—making sure your agents only proceed when the data is ready.

Connect Vertex AI Vector Search to Google ADK for enterprise data actioning on BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vertex AI Vector Search MCP to Google ADK

Create your Vinkius account to connect Vertex AI Vector Search 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 Vertex AI Vector Search with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vector Similarity with MCP Server

The `search_nearest_neighbors` tool gives your agent the power to query semantic embeddings directly. You supply an endpoint ID, index ID, and a vector array as JSON. This lets your enterprise agents act on data beyond simple SQL joins, searching contextually across massive datasets.

Administering Vertex Index Endpoints

Use `list_index_endpoints` to confirm the active connection points for your vector indexes within Google Cloud. This is key when building reliable agents that depend on specific service endpoints. You can also use `get_index_details` to review the full configuration settings of a target index.

Discovering All Vector Indexes

Need an inventory? The `list_vector_indexes` tool lets your agent list every single vector index deployed in the project. It provides a necessary overview, ensuring that all data sources you want to search are accounted for and available.

Setup guide

Set up Vertex AI Vector Search 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 Vertex AI Vector Search 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="Vertex AI Vector Search_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Vertex AI Vector Search 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 Vertex AI Vector Search. 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 Vertex AI Vector Search 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 Vertex AI Vector Search MCP in Google ADK

Your agent invokes `search_nearest_neighbors` when it needs contextual answers. It sends the required endpoint ID, index ID, and query vector to find the closest matches in your embeddings.

The MCP Server manages highly specific operational data: vector embedding configurations, index metadata, and raw search vectors. This is all handled within the secure Google Cloud environment.

Yes. The `list_vector_indexes` tool allows your agent to pull a comprehensive list of every vector index in the project, making discovery seamless for your enterprise workflow.

It does. The `list_vector_operations` tool allows your agent to check on long-running processes—like index creation or updates—making sure your agents only proceed when the data is ready.

It's built for it. By integrating vector search, you allow Gemini models to reason over contextually rich data pulled directly from your BigQuery sources.

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