How to Use the UtilityAPI MCP in Google ADK

Q: How do I list available meters for a customer using UtilityAPI and Google ADK?

You run listmeters to pull all connected utility service points. The result gives you the meteruid, which is your primary key for querying usage data across the MCP Server.

Q: What types of financial information can I get with UtilityAPI and Google ADK?

You can pull detailed bills using getbills (total cost, start/end dates) or check your account spending via getbillingsummaries. Both tools are essential for tracking utility finances.

Q: How does the UtilityAPI work with Google ADK for time-series analysis?

The getintervals tool pulls granular data—hourly or 15-minute usage readings. This raw, high-frequency data is what you need when your agent models energy demand over time.

Q: If I'm building a pipeline with Google ADK, where do I start the process?

You begin by using createauthform to set up the data sharing agreement. This returns a form UID that you need before any subsequent queries will succeed.

Action utility billing and usage data in BigQuery with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UtilityAPI MCP to Google ADK

Create your Vinkius account to connect UtilityAPI 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 UtilityAPI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get combined billing and interval data (MCP Server)

Need a complete picture of a customer’s energy life cycle? The `get_meter_data` tool combines results from both bills and intervals in one call. You just need the meter UID, and it gives you everything—financial records plus time-series usage readings. This is super useful when your Google ADK agent needs to build a holistic profile of energy consumption.

Track authorization status with Google ADK

Use `get_events` to monitor the entire data collection lifecycle. This tool provides webhooks for new authorizations, when meter data becomes available, and if any errors occurred. It’s crucial for debugging or building real-time alerts. Knowing the status of data collection prevents your agent from running incomplete reports.

List supported utility companies (MCP Server)

Before you write a single query, check which utilities are supported. `list_utilities` returns names and codes for major providers—like PG&E or National Grid—that the UtilityAPI supports. This ensures your agent uses the correct code when creating authorization forms. This prevents failed API calls right out of the gate.

Setup guide

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

You run `list_meters` to pull all connected utility service points. The result gives you the `meter_uid`, which is your primary key for querying usage data across the MCP Server.

You can pull detailed bills using `get_bills` (total cost, start/end dates) or check your account spending via `get_billing_summaries`. Both tools are essential for tracking utility finances.

The `get_intervals` tool pulls granular data—hourly or 15-minute usage readings. This raw, high-frequency data is what you need when your agent models energy demand over time.

You begin by using `create_auth_form` to set up the data sharing agreement. This returns a form UID that you need before any subsequent queries will succeed.

You access three main types: usage intervals (kWh/therms), billing history, and general meter metadata. All of this is exposed through the UtilityAPI.

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