How to Use the Vald MCP in Google ADK

Q: How do I search for vectors with Vald and Google ADK?

Use searchvectors. You provide a query vector as a JSON array of floats, and the MCP Server performs a nearest neighbor search. Your agent gets back the most similar records right away.

Q: What happens if I need to delete data using Vald and Google ADK?

The deletevector action permanently removes vector data from the Vald index. It's a one-way street, so double-check your IDs before running it.

Q: Can my agent check the status of Vald using Google ADK?

Yes. Calling getengineinfo retrieves the full operational information and health report for the Vald engine, ensuring everything is stable for your enterprise workflow.

Build enterprise agents that query, insert, and manage dense vectors using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to Google ADK

Create your Vinkius account to connect Vald 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 Vald with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying Vectors with the MCP Server

The `search_vectors` tool finds nearest neighbors in your index. You pass it a query vector formatted as a JSON array of floats, and Vald executes the similarity search against all stored data. This allows your Gemini-powered agent to pull highly relevant context from massive datasets without complex joins.

Managing Vector Data with Google ADK

Need to add new information? `insert_vector` is the tool. Just give it a unique ID and your vector data as a JSON array, and Vald indexes it instantly. If source material changes, use `update_vector`. You specify an existing ID and pass in the new vector array to overwrite what's currently stored.

Inspecting Vald Engine Details

You can check operational health with `get_engine_info`, which reports on the full status of the Vald engine. It helps your team confirm everything is up and running. Want to grab specific records? The `get_vector_details` tool lets you pull the raw vector data for any given ID, perfect for debugging or auditing.

Setup guide

Set up Vald 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 Vald 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="Vald_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Vald 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 Vald. 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 Vald 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 Vald MCP in Google ADK

Use `search_vectors`. You provide a query vector as a JSON array of floats, and the MCP Server performs a nearest neighbor search. Your agent gets back the most similar records right away.

The `delete_vector` action permanently removes vector data from the Vald index. It's a one-way street, so double-check your IDs before running it.

Yes. Calling `get_engine_info` retrieves the full operational information and health report for the Vald engine, ensuring everything is stable for your enterprise workflow.

This server works with dense vectors. The core data type you manage is the vector itself—a JSON array of floats—which gets tracked by a unique ID.

The MCP Server handles the secure storage of your dense vector data. You manage access through specific tools like `get_vector_details` and `delete_vector`, giving you full control.

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