How to Use the OpenEI MCP in Pydantic AI

Type-safe energy intelligence: use Pydantic AI to query OpenEI utility rates with runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect OpenEI MCP to Pydantic AI

Create your Vinkius account to connect OpenEI to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup OpenEI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Strict type-safe tariff lookups

Every response from `get_residential_rates` is validated against your Pydantic schemas. If the data is malformed or missing fields, the agent catches it instantly. This ensures your financial models never break due to unexpected API responses. You get clean, typed data every time you request a rate structure.

Reliable rate detail extraction

Use `get_rate_detail` to pull complex tariff structures into your agent. Pydantic AI enforces the expected structure, preventing your logic from processing bad or incomplete data. It forces your code to handle errors before they reach your proposal engine. You'll know immediately if a rate plan is missing crucial demand charge fields.

Industrial cost modeling

Your agent calls `get_industrial_rates` to retrieve complex power factor and demand charge data. Pydantic AI validates these numerical inputs against your strict constraints. This is essential for high-stakes industrial projects. You can trust the numbers in your model because the framework validates them at the source.

Setup guide

Set up OpenEI 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": {
        "openei-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent OpenEI 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 OpenEI. 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 OpenEI 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 OpenEI MCP in Pydantic AI

Install the slim package and use the MCPToolset. It provides a unified way to connect your agent to the server, ensuring all incoming data is validated against your models.

The agent will raise a validation error immediately. This stops the process before bad data can corrupt your energy calculations.

Yes, it supports SSE transports for real-time communication. This keeps your agent responsive while it fetches rate data for your solar models.

Absolutely. You can write a logic flow where the agent first calls `search_utilities_by_name` and then feeds the result into `get_utility_rates` for a complete analysis.

The server operates in a zero-trust environment. Your address data is only used to compute the specific rate lookup and is discarded immediately after the response is validated.

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