How to Use the ItemPath MCP in Google ADK

Q: How do I initialize the ItemPath MCP Server inside a Google ADK project?

Install the package with pip install google-adk and create an instance of McpToolset using StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into the tools list of your LlmAgent. This exposes the entire suite of 10 inventory tools to your Gemini model.

Q: Can I restrict the Google ADK to only use specific ItemPath tools?

Yes, you can use the optional toolnames filter parameter when creating your McpToolset. Pass toolnames="getmaterial", "listmaterials" to prevent the agent from viewing order or transaction data.

Q: How does Gemini's long context window work with ItemPath data?

You can retrieve massive datasets using listtransactions or listbatches and feed them directly into the agent's context. Gemini models handle over 1 million tokens, allowing the agent to analyze months of warehouse logs in a single turn without running out of memory.

Connect Gemini models to ItemPath warehouse data using the Google ADK to analyze massive inventory logs with long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ItemPath MCP to Google ADK

Create your Vinkius account to connect ItemPath 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 ItemPath with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-million token inventory analysis via Google ADK

`list_transactions` feeds deep historical stock changes directly into Gemini's massive context window for long-term trend analysis. The Google ADK lets your enterprise agent ingest thousands of transaction lines without hitches, mapping physical stock movements against your BigQuery datasets. You pass the MCP Server toolset directly into your `LlmAgent` initialization. This allows the model to cross-reference raw transaction logs with actual warehouse layout maps retrieved via `list_locations`.

Restrict tool exposure to secure warehouse operations

`list_orders` can be isolated from other administrative functions by applying the `tool_names` filter during toolset initialization. This ensures your customer service agent only sees order-related actions and cannot access sensitive backend tables. The agent uses `get_order` to pull real-time picker information and target locations when troubleshooting delivery delays. By restricting the toolset, you prevent the LLM from accidentally triggering unauthorized inventory adjustments.

Verify connection health across Google Cloud pipelines

`get_me` validates your API connection health and verifies the active user identity within your automated Google Cloud pipelines. If a Cloud Function triggers an inventory check, this tool confirms the credentials are valid before executing any data retrievals. Your agent can then safely call `list_materials` to audit product codes or inspect perishable goods using `list_batches`. This structured flow keeps your GCP-hosted inventory workflows stable and secure.

Setup guide

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

Install the package with `pip install google-adk` and create an instance of `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into the `tools` list of your `LlmAgent`. This exposes the entire suite of 10 inventory tools to your Gemini model.

Yes, you can use the optional `tool_names` filter parameter when creating your `McpToolset`. Pass `tool_names=["get_material", "list_materials"]` to prevent the agent from viewing order or transaction data.

The ADK supports both Stdio and HTTP transports natively. For serverless environments like Google Cloud Functions, use the HTTP transport with your Vinkius endpoint token to maintain stateless execution.

You can retrieve massive datasets using `list_transactions` or `list_batches` and feed them directly into the agent's context. Gemini models handle over 1 million tokens, allowing the agent to analyze months of warehouse logs in a single turn without running out of memory.

Your warehouse data, including material counts and order histories, is transmitted via HTTPS directly to your private Google Cloud environment. Vinkius secures the endpoint with an ephemeral, zero-trust MCP Server sandbox, ensuring no credentials or raw payloads are ever persisted on external servers.

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