How to Use the Kargo MCP in Google ADK

Q: How do I register the Kargo MCP toolset in Google ADK?

Install the package using pip install google-adk and import McpToolset with your Vinkius HTTP URL. Pass that toolset directly into the tools list of your LlmAgent to let Gemini models call operations like listshipments or updatelogistics natively.

Q: Can I filter which tools are exposed to my agent?

Yes, you can use the toolnames parameter in your StreamableHttpServerParameters to limit access. For example, you can expose only getdevicestatus and listdevices to keep your agent focused purely on monitoring hardware.

Connect Gemini's million-token context to Kargo using Google ADK to manage warehouse fleets and BigQuery logistics data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kargo MCP to Google ADK

Create your Vinkius account to connect Kargo 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 Kargo with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK massive context reasoning

Processing large shipping manifests is straightforward when your Google ADK agent uses `list_shipments` to pull data into Gemini's context window. The agent can cross-reference `list_shipments` and `list_orders` in a single run. This allows the model to spot systemic delays across your supply chain that smaller models miss. It looks at the big picture, combining live API data with historical warehouse trends.

BigQuery and dock sensor integration

Syncing physical dock sensor data with your database is simple when your agent queries `get_device_status` and `list_devices`. Google ADK lets your agent query those analytical databases and match them against live dock hardware status. Your agent can detect if a physical gate is malfunctioning and update your BigQuery records instantly. By using `update_logistics`, the agent syncs the physical reality of your loading docks back to your central ERP.

Multi-facility coordination

Mapping out your distribution network is fast when your agent uses `list_facilities` to coordinate multiple locations. Querying `list_payload_logs` ensures all locations are syncing properly. You can restrict the exposed tools using the `tool_names` filter in the `McpToolset` configuration. This ensures your regional facility agents only touch the tools they need, like `get_order`, without risking unauthorized global changes.

Setup guide

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

Install the package using `pip install google-adk` and import `McpToolset` with your Vinkius HTTP URL. Pass that toolset directly into the `tools` list of your `LlmAgent` to let Gemini models call operations like `list_shipments` or `update_logistics` natively.

Yes. Gemini's 1M+ token window allows the agent to ingest hours of warehouse logs. The agent can call `list_payload_logs` or `list_orders`, pull the entire payload, and analyze shipping discrepancies without running out of memory.

Your Google Cloud environment never sees the raw Kargo credentials. The Google ADK agent speaks directly to Vinkius via an HTTP transport, using a single secure token to authenticate and execute tools like `get_carrier_info`.

Yes, you can use the `tool_names` parameter in your `StreamableHttpServerParameters` to limit access. For example, you can expose only `get_device_status` and `list_devices` to keep your agent focused purely on monitoring hardware.

It goes straight to your agent. Vinkius runs the MCP Server in an isolated, ephemeral V8 sandbox that destroys itself after execution. Your facility lists from `list_facilities` and order details from `get_order` are never cached or stored on Vinkius infrastructure.

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