How to Use the OpenEI MCP in OpenAI Agents SDK

Get accurate utility rate data directly inside your OpenAI Agents SDK workflows for precise solar and energy economic modeling.

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 OpenAI Agents SDK

Create your Vinkius account to connect OpenEI to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated rate discovery for agents

Your agent identifies local utility providers instantly using `search_utilities_by_name`. It grabs the right utility ID without manual lookup, feeding that data directly into your cost analysis logic. This removes the guesswork from initial feasibility studies. Your agent pulls verified data, ensuring your financial models start with accurate numbers instead of stale assumptions.

Geospatial tariff lookups

Feed a coordinate pair to `get_rates_by_coordinates` and watch your agent extract current residential and commercial tariffs. It handles the mapping between physical locations and complex utility service territories. This is where developers lose money—using outdated rate sheets. Your agent gets the latest data, keeping your projections aligned with actual grid pricing.

Detailed structure analysis

Once a rate ID is identified, use `get_rate_detail` to pull the full tariff breakdown. Your agent parses seasonal variations, demand charges, and time-of-use periods automatically. Stop guessing how demand charges impact ROI. The agent ingests these parameters, allowing you to build robust, site-specific energy proposals that hold up under scrutiny.

Setup guide

Set up OpenEI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all OpenEI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives OpenEI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate OpenEI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="OpenEI Agent",
            instructions="You have access to OpenEI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the MCPServerStreamableHttp class to point your agent at the server URL. Once you pass the server to your agent constructor, the SDK handles tool discovery automatically.

Yes, by providing real-time tariff data. Instead of relying on static spreadsheets, your agent fetches live utility rates, reducing the margin of error in your financial projections.

It does. Because the server exposes specific tools, you can wrap them in your existing validation logic. This ensures your agent only acts on approved rate data before executing a proposal.

The server returns structured JSON which the SDK handles as standard tool output. You should implement your own parsing logic to map these results into your internal economic models.

Your address is sent only to fetch the specific utility data required for the request. We do not store your geocoded inputs or project details after the transaction completes.

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