How to Use the Arcadia Utility Cloud MCP in Google ADK

Q: How do I write Arcadia Utility Cloud meter data to BigQuery using Google ADK?

Your Gemini agent extracts the metrics using getmeterdata. You then configure a separate custom tool in your Google ADK environment that takes that JSON output and inserts it into your BigQuery dataset.

Connect Arcadia Utility Cloud to Google ADK. Feed long-context Gemini agents with historical meter data and statements.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arcadia Utility Cloud MCP to Google ADK

Create your Vinkius account to connect Arcadia Utility Cloud 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 Arcadia Utility Cloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Utility Infrastructure

The `list_accounts` and `list_meters` tools expose your physical utility footprint to Gemini. Your Google ADK agent calls these functions to build an internal graph of every tracked building and its associated hardware. Feeding this topology into a massive token context window allows the model to understand complex multi-site energy grids. Exposing these endpoints requires minimal setup using the MCP toolset. Passing your Vinkius HTTP URL to `StreamableHttpServerParameters` connects the infrastructure immediately. You can then write the resulting meter lists directly into BigQuery tables for enterprise reporting.

Analyze Meter Data via MCP Server

Executing `get_meter_data` pulls granular consumption metrics straight into your Vertex AI pipelines. The agent requests specific date ranges for a target meter, receiving raw kilowatt-hours or water gallon usage. Correlating these usage spikes with external datasets becomes trivial when the AI client handles the data extraction natively. Restricting MCP tool access keeps your agents focused on specific tasks. Applying the `tool_names` filter in Google ADK ensures a data-ingestion agent only sees the meter reading functions. This prevents the system from accidentally querying billing statements when it should be analyzing power grids.

Ingest Billing Statements

Running `list_statements` followed by `get_statement` retrieves the metadata for every utility bill in your Arcadia account. Gemini reads the invoice dates, totals, and line items, using its massive context window to compare year-over-year spending across dozens of locations. Financial agents parse these records to detect billing errors automatically. Enterprise deployments rely on secure, predictable data pipelines. The Vinkius platform handles authentication, so your Google ADK implementation only needs a single endpoint token to read the statements. Your agent fetches the invoices over the HTTP transport and pushes the structured data straight to your cloud storage.

Setup guide

Set up Arcadia Utility Cloud 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 Arcadia Utility Cloud 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="Arcadia Utility Cloud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Arcadia Utility Cloud 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 Arcadia. 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 Arcadia Utility Cloud 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 Arcadia Utility Cloud MCP in Google ADK

Install google-adk using pip. Create an McpToolset instance using your Vinkius HTTP endpoint and pass it to the tools parameter of your LlmAgent.

You shouldn't expose everything blindly, so filter the available functions during initialization. Use the tool_names parameter in Google ADK to expose only get_meter_data if you want to block access to billing statements.

The framework supports both Stdio and HTTP transports natively. You'll use StreamableHttpServerParameters to connect to the managed Vinkius instance.

Your Gemini agent extracts the metrics using get_meter_data. You then configure a separate custom tool in your Google ADK environment that takes that JSON output and inserts it into your BigQuery dataset.

This integration accesses granular kilowatt-hour readings and physical meter IDs. Vinkius routes these requests through a stateless V8 isolate, ensuring your enterprise energy patterns are never stored on disk or cached after the agent receives the response.

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