How to Use the Kyte MCP in Google ADK

Query store inventory and analyze transaction histories directly inside your Google ADK agent pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kyte MCP to Google ADK

Create your Vinkius account to connect Kyte 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 Kyte with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze inventory with Google ADK and BigQuery

`list_kyte_products` feeds your entire product catalog directly into Gemini's massive 1M-token context window. This allows the model to map your inventory against historical sales trends stored in BigQuery without hitting context limits. The agent uses `get_inventory_status` to cross-reference current stock levels with predicted demand. You get instant restock recommendations based on actual warehouse data, bypassing manual spreadsheet updates entirely.

Run deep financial audits through this MCP Server

`list_financial_transactions` extracts your complete transaction ledger for ingestion by Gemini. Because the Google ADK handles long-context reasoning, the agent analyzes thousands of raw payment logs in a single pass. This MCP Server connection lets you run complex fraud detection patterns across your entire POS history. The agent flags anomalous transactions and matches them against customer profiles without slowing down your live store.

Track store operations across Google Cloud

`get_kyte_store_status` provides a real-time health check of your retail operations. The Google ADK parses this status payload to trigger automated alerts in your Google Cloud monitoring console if the store goes offline. If the status changes, the agent pulls `list_kyte_orders` to check if pending deliveries are stalling. This keeps your logistics pipeline moving by automating operational checks directly inside your cloud infrastructure.

Setup guide

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

Use the McpToolset class with the streamable HTTP server parameters pointing to your Vinkius endpoint. Pass this toolset directly into your LlmAgent to let Gemini access your POS data, which will initialize the MCP Server using the HTTP transport.

Yes, the Google ADK leverages Gemini's 1M-token context window to process months of transaction data at once. The model reads the output of `list_kyte_products` and correlates it with your cloud databases.

You can restrict access by passing a list of allowed tool names to the toolset configuration. This ensures the model only accesses `get_kyte_store_status` while blocking financial tools.

No, this setup requires an internet connection to reach the hosted MCP Server on Vinkius. The gateway acts as the secure bridge between Google Cloud and your POS account.

Your product pricing, catalog structure, and store status are processed inside your private Google Cloud tenant. No data is used to train public models, and all API keys are stored in Secret Manager.

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