How to Use the GrazeCart MCP in Google ADK

Q: How do I set up the GrazeCart MCP Server with Google ADK?

Install google-adk and configure McpToolset with the Vinkius HTTP transport URL. Pass the toolset directly to your LlmAgent to instantly expose tools like listproducts to your Gemini model.

Q: Can I use Google ADK to sync GrazeCart with BigQuery?

Yes. Your agent can fetch customer records using listcustomers, format the payload, and write it directly to BigQuery. This makes it easy to combine your farm store sales with other marketing data.

Q: Can I filter which GrazeCart tools are exposed to Google ADK?

Yes. Use the toolnames parameter in your McpToolset configuration to limit access. You can restrict your agent to read-only tools like listpickuplocations if you want to prevent accidental updates.

Connect Google ADK with Gemini to manage GrazeCart store inventory and analyze local delivery zones in a long-context workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GrazeCart MCP to Google ADK

Create your Vinkius account to connect GrazeCart 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 GrazeCart with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze large-scale GrazeCart operations via Google ADK

Gemini's million-token context window lets your agent process your entire store history at once. The agent calls `list_orders` and `list_customers` to pull raw sales records directly into your Google Cloud environment. You can feed this data into BigQuery to find buying trends. Your Google ADK agent can then use `get_customer` to build targeted profiles based on what people actually buy.

Coordinate complex farm logistics and pickup hubs

Managing local food distribution requires knowing your physical footprint. Your agent calls `list_delivery_zones` and `list_pickup_locations` to map out where your trucks actually go. When a customer changes their mind, the agent runs `update_order` to switch their pickup spot. This keeps your delivery drivers on the right path without you opening the admin panel.

Automate stock adjustments with this MCP Server

Keep your meat and produce counts accurate across your warehouse with this MCP Server. The agent uses `get_product` to inspect specific cuts and `list_products` to see the whole catalog. When new stock arrives, it calls `update_inventory` to update the numbers. Your agent handles the tedious entry work so you can focus on packing orders.

Setup guide

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

Install `google-adk` and configure `McpToolset` with the Vinkius HTTP transport URL. Pass the toolset directly to your `LlmAgent` to instantly expose tools like `list_products` to your Gemini model.

Yes. Your agent can fetch customer records using `list_customers`, format the payload, and write it directly to BigQuery. This makes it easy to combine your farm store sales with other marketing data.

The model reads the tool definitions, decides which action to take, and calls them. For example, it might call `get_order` to check a balance, then call `charge_order` to collect the payment.

Yes. Use the `tool_names` parameter in your `McpToolset` configuration to limit access. You can restrict your agent to read-only tools like `list_pickup_locations` if you want to prevent accidental updates.

Yes. Vinkius runs the MCP Server in an isolated sandbox, keeping your API keys hidden from the LLM. Your order details and customer names are processed over secure HTTPS and never used for public model training.

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