How to Use the UtilityAPI MCP in LangChain

Q: How does UtilityAPI help LangChain track customer data access?

You use listauthorizations to see who has granted access. If you need more detail, run getevents. This tells your LangChain agent exactly when an authorization was created or if the meter data collection finished successfully.

Q: Can I get a full picture of energy usage in LangChain?

Yeah. The getmeterdata tool combines both billing history and granular interval readings into one shot. Your LangChain agent just needs the meter UID to pull everything it requires for deep analysis.

Q: When developing, how can I test UtilityAPI with LangChain?

Run createauthform first, then use that output in testformsubmission. This generates a referral code. Your LangChain client can then use that code to verify the setup without needing real customer data.

Build multi-step reasoning pipelines for LangChain agents using UtilityAPI.

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 LangChain

Create your Vinkius account to connect UtilityAPI to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Complex Data Retrieval with MCP Server

Need to figure out a customer's total energy cost? You can chain together multiple calls. First, run `list_meters` to grab the necessary meter IDs; then use those IDs in `get_bills`. This lets your LangChain agent build an accurate picture of their spending. This sequence works because the output of one tool—like a list of meters—becomes the precise input for the next. It's ideal for agents that need to decide *which* data points to pull and in what order.

Monitor Authorization Status via LangChain

When you set up new data sharing, you don't want to wait around. Use `create_auth_form` to get the initial setup going. Then, your agent can continuously check for status updates by calling `get_events`. This lets your system know immediately when a customer has actually authorized access or if something broke. It’s better than polling manually. Your LangChain chain watches these events and triggers the next step—like running `activate_historical_collection`—only when the data is ready.

Analyze Detailed Usage Patterns for LangChain

To build a deep energy model, you can't just rely on the monthly bill. The `get_intervals` tool delivers granular usage readings, usually every 15 minutes or hourly. Your agent grabs this time-series data and passes it to other tools in the chain for calculation. This gives you peak demand information that billing summaries miss completely. It’s how your LangChain application goes from 'read' to 'calculate'.

Setup guide

Set up UtilityAPI MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes UtilityAPI tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "utilityapi-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent UtilityAPI transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You use `list_authorizations` to see who has granted access. If you need more detail, run `get_events`. This tells your LangChain agent exactly when an authorization was created or if the meter data collection finished successfully.

Yeah. The `get_meter_data` tool combines both billing history and granular interval readings into one shot. Your LangChain agent just needs the meter UID to pull everything it requires for deep analysis.

Run `create_auth_form` first, then use that output in `test_form_submission`. This generates a referral code. Your LangChain client can then use that code to verify the setup without needing real customer data.

The system supports over 100 US utilities, including major players like PG&E and Con Edison. You find their specific codes using `list_utilities` before you can proceed with any data queries in your MCP Server.

The server handles utility billing, usage interval data (kWh or therms), and customer authorization records. Always remember that access requires a specific meter UID or an authorized customer ID.

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