How to Use the OpenEI MCP in LangChain

Q: How do I connect the OpenEI MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize a MultiServerMCPClient pointing to the OpenEI endpoint, call gettools(), and pass the array to your ReAct agent.

Q: Can LangChain agents automatically find rates for a list of addresses using OpenEI?

Yes. Your agent loops through the list and calls getratesbyaddress for each location. LangSmith logs the latency and token usage for every individual API call.

Q: How does LangChain handle complex demand charges from OpenEI?

Calling getratedetail pulls the full tariff structure into the context window. Your chain extracts the specific seasonal demand charges and passes them to a math tool for accurate cost projection.

Build ReAct agents in LangChain that query OpenEI utility rates and calculate solar ROI across complex multi-step pipelines.

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 LangChain

Create your Vinkius account to connect OpenEI to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Map utility territories with LangChain

`search_utilities_by_name` and `list_utilities` let your ReAct agent identify the exact power company serving a target region. Your pipeline grabs the utility IDs and feeds them directly into the next step of the chain. You don't have to manually cross-reference state databases anymore. The agent decides which sector to query based on previous inputs. Passing those IDs into `get_utility_detail` pulls down contact information and generation resources. LangSmith traces the whole execution path, so you see exactly how many tokens the lookup consumed.

Extract exact tariffs using the OpenEI MCP Server

`get_rates_by_address` takes a raw street location and returns every available tariff option for that specific site. Your chain parses the JSON output and routes it to specific calculators for residential or commercial modeling. The data covers everything from flat tiers to complex time-of-use periods. Hitting `get_rate_detail` exposes the raw math behind the bill. This tool pulls the energy charges, demand spikes, and fixed fees required for accurate financial modeling. You plug this directly into your discounted cash flow node without copying and pasting from PDF rate sheets.

Model industrial and commercial load profiles

`get_commercial_rates` and `get_industrial_rates` pull the heavy-duty tariffs needed for large-scale energy analysis. These endpoints return the demand charges and power factor adjustments that destroy project economics if calculated wrong. Your agent pulls the rates, runs the math, and outputs a clean financial summary. If the site lacks a postal address, `get_rates_by_coordinates` handles the geo-spatial lookup automatically. The LangChain pipeline just passes the lat/lon tuple, and the MCP server figures out the jurisdiction. You get back the exact rate structure needed to size a battery storage system.

Setup guide

Set up OpenEI 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 OpenEI 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({
    "openei-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 OpenEI 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 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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize a `MultiServerMCPClient` pointing to the OpenEI endpoint, call `get_tools()`, and pass the array to your ReAct agent.

Yes. Your agent loops through the list and calls `get_rates_by_address` for each location. LangSmith logs the latency and token usage for every individual API call.

The tool returns all available options in the JSON response. You write a prompt instructing the agent to filter the array based on specific criteria, like picking the cheapest time-of-use plan.

Calling `get_rate_detail` pulls the full tariff structure into the context window. Your chain extracts the specific seasonal demand charges and passes them to a math tool for accurate cost projection.

The server processes physical addresses and GPS coordinates ephemerally to query the database. It drops the location data immediately after returning the tariff structures. Vinkius runs the integration in a zero-trust V8 isolate sandbox.

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