How to Use the Fixably MCP in Google ADK

Q: How do I configure the Fixably MCP Server with the Google ADK?

Install the library using pip install google-adk. Create an instance of McpToolset pointing to your Vinkius HTTP URL, and pass it to your LlmAgent tools array to register the MCP tools with Gemini.

Q: Can I limit which Fixably tools Google ADK can access?

Yes, you can use the optional toolnames filter when initializing your toolset. This allows you to expose only read-only tools like getorder while restricting write actions to authorized agents.

Q: How does the agent track physical device locations?

The agent calls changeinternallocation to update the physical department or shelf where a device is stored. It verifies the current location by calling getorder to ensure the physical status matches the MCP Server state.

Q: Where is my inventory and order data stored during processing?

Your stock levels, warehouse locations accessed via getstock, and order files remain strictly within your Google Cloud boundaries and the secure Vinkius V8 sandbox. Authentication is handled via a single secure token, preventing unauthorized access to your physical inventory databases.

Bring Gemini's million-token context to Fixably using Google ADK to analyze massive repair histories and manage inventory.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fixably MCP to Google ADK

Create your Vinkius account to connect Fixably 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 Fixably with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Deep Repair Histories with Google ADK

The agent uses `list_orders` to pull hundreds of historical repair records and feeds them into Gemini's massive context window to identify recurring hardware failure patterns. When a technician encounters a complex issue, the agent calls `get_order` to retrieve the full lifecycle of that specific device. It then uses `add_order_note` to write diagnostic suggestions based on similar past cases, keeping all MCP actions logged directly in your ticket history.

Sync Warehouse Physical Locations with BigQuery Data

This system uses `list_stocks` to get current inventory locations and updates physical movements using `change_internal_location`. By combining this with Vertex AI, your agent can predict inventory shortages. It checks current levels via `get_stock` and cross-references them with historic parts usage, updating the order status with `update_order` when parts are successfully allocated.

Secure Enterprise Customer Data Processing

Your agent executes `list_customers` to find customer profiles and `get_customer` to retrieve specific contact details and service preferences. Your agents can use this MCP Server to manage large customer directories without leaving your secure Google Cloud environment. When a customer requests an update, the agent scans for attached documentation using `list_order_files`. Then, the agent synthesizes this information to draft personalized email updates, ensuring your support team has the exact context they need.

Setup guide

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

Install the library using `pip install google-adk`. Create an instance of `McpToolset` pointing to your Vinkius HTTP URL, and pass it to your `LlmAgent` tools array to register the MCP tools with Gemini.

Yes, you can use the optional `tool_names` filter when initializing your toolset. This allows you to expose only read-only tools like `get_order` while restricting write actions to authorized agents.

The SDK utilizes high-throughput HTTP transports to fetch data via `list_stock_products` rapidly. Gemini's long-context window allows the agent to process thousands of stock lines in a single turn without hitting context limits.

The agent calls `change_internal_location` to update the physical department or shelf where a device is stored. It verifies the current location by calling `get_order` to ensure the physical status matches the MCP Server state.

Your stock levels, warehouse locations accessed via `get_stock`, and order files remain strictly within your Google Cloud boundaries and the secure Vinkius V8 sandbox. Authentication is handled via a single secure token, preventing unauthorized access to your physical inventory databases.

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