How to Use the UtilityAPI MCP in Pydantic AI

Q: How do I get interval usage data using UtilityAPI and Pydantic AI?

You call getintervals, passing the necessary meter UID. This returns granular energy usage readings over time, which your agent can then validate against defined Pydantic schemas for accuracy.

Q: What is the process flow when using UtilityAPI and Pydantic AI?

You first use listutilities to get a valid utility code. Then, you pass that code to createauthform to start the authorization agreement before querying any data.

Q: How does Pydantic AI handle billing data from UtilityAPI?

The getbills tool provides cost and usage totals. Because of Pydantic's runtime validation, you can trust that the returned fields—like total cost or energy usage—match the expected structure.

Q: Can I test my agent setup with UtilityAPI using Pydantic AI?

Yes. You run testformsubmission. This simulates a customer authorization flow and returns a referral code, allowing you to verify your form configuration without going live.

Type-safe utility data access for production agents with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect UtilityAPI to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor authorization status via MCP Server

Need to know if the customer authorized their account? Use `list_authorizations` to check which customers have granted data access. The results show who they are and let you track specific referral codes. This visibility is critical for your agent when determining if it has permission to run queries.

Get utility billing history with Pydantic AI

`get_bills` returns structured data about total costs, usage amounts (kWh or therms), and date ranges. Since you're using Pydantic AI, you get guaranteed validation on these financial records—no hallucinated fields. This makes analyzing customer spending predictable and reliable.

Retrieve detailed meter information from MCP Server

Start by identifying the correct service connection using `list_meters`. This returns essential metadata like the utility name, fuel type (electric/gas), and the unique `meter_uid` you must use in subsequent calls. This is your starting point for almost every data retrieval task.

Setup guide

Set up UtilityAPI MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "utilityapi-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to UtilityAPI tools.",
)

result = await agent.run("List recent UtilityAPI transactions")
print(result.output)

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 Pydantic AI

You call `get_intervals`, passing the necessary meter UID. This returns granular energy usage readings over time, which your agent can then validate against defined Pydantic schemas for accuracy.

You first use `list_utilities` to get a valid utility code. Then, you pass that code to `create_auth_form` to start the authorization agreement before querying any data.

The `get_bills` tool provides cost and usage totals. Because of Pydantic's runtime validation, you can trust that the returned fields—like total cost or energy usage—match the expected structure.

Yes. You run `test_form_submission`. This simulates a customer authorization flow and returns a referral code, allowing you to verify your form configuration without going live.

The server touches utility billing amounts (dollars), energy usage values (kWh/therms), meter identifiers (`meter_uid`), and authorization records.

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