How to Use the Constructor MCP in Google ADK

Q: How do I configure the Constructor MCP Server within a Google ADK agent?

You initialize McpToolset with the Vinkius HTTP stream parameters pointing to your server. Then, pass that toolset object into your LlmAgent tools array to expose the search capabilities.

Q: Does Google ADK support filtering specific Constructor MCP tools?

Yes, you can use the optional toolnames filter in the toolset configuration. This lets you expose only specific tools like customsearch while hiding backend tools like billing rules.

Q: How does the agent handle complex search sorting rules?

The agent calls searchsorted to retrieve structured rules. This lets Gemini analyze how active billing rules affect product placement in search results.

Connect Gemini enterprise agents to Constructor via Google ADK for long-context search analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Constructor MCP to Google ADK

Create your Vinkius account to connect Constructor 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 Constructor with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze massive catalog arrays using Google ADK

Analyzing large enterprise catalogs starts with running `browse_category` to pull JSON payloads of customer bindings. Your agent can process these payloads alongside your BigQuery warehouse data inside Gemini's million-token context window. Using this MCP Server, the agent analyzes thousands of items at once. It matches live category structures against historical Google Cloud datasets without losing track of your specific inventory rules.

Audit gateway authentication across search arrays

Securing search endpoints requires calling `browse_collection` to check active arrays against native gateway authentication rules. This integration lets your Gemini agent run these checks and flag anomalies in real time. Because the ADK runs natively inside Vertex AI, you can cross-reference these collection arrays with your cloud security logs. The agent spots configuration mismatches instantly, ensuring only authenticated users see restricted catalog items.

Run deep filtered product searches with Gemini

Finding products with specific dimensions requires calling `search_filtered` to restrict arrays to exact features. The tool pulls clean JSON structures directly into the agent's context window, removing the need for manual parsing. This allows your Google ADK agent to build complex search queries on the fly. It combines these filtered results with Vertex AI models to predict which catalog items will perform best based on past search trends.

Setup guide

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

You initialize `McpToolset` with the Vinkius HTTP stream parameters pointing to your server. Then, pass that toolset object into your `LlmAgent` tools array to expose the search capabilities.

Yes, because the ADK runs in the Google Cloud ecosystem. Your agent can pull catalog data using `search_products` and immediately run SQL queries in BigQuery to cross-reference stock levels.

Yes, you can use the optional `tool_names` filter in the toolset configuration. This lets you expose only specific tools like `custom_search` while hiding backend tools like billing rules.

The agent calls `search_sorted` to retrieve structured rules. This lets Gemini analyze how active billing rules affect product placement in search results.

Your e-commerce catalog data is processed inside secure, ephemeral V8 sandboxes. Vinkius uses a zero-trust architecture that never writes your search logs or inventory arrays to persistent disks, keeping your enterprise cloud perimeter clean.

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