How to Use the OpenEI MCP in LlamaIndex

Q: How do I integrate OpenEI with my LlamaIndex application?

Run pip install llama-index-tools-mcp and set up a BasicMCPClient. Create an McpToolSpec, convert it via totoollistasync(), and hand it to your FunctionAgent.

Q: Can LlamaIndex store OpenEI rate data for offline querying?

The framework indexes the JSON responses from tools like getutilityrates into your vector store. You query the indexed data repeatedly without hitting the external API again.

Q: How does LlamaIndex handle the massive JSON payloads from OpenEI?

It chunks the tariff structures returned by getratedetail and embeds them as searchable nodes. Semantic search retrieves only the specific seasonal or demand charges relevant to the user's prompt.

Q: Can I filter which OpenEI tools my LlamaIndex agent uses via the MCP Server?

You pass an allowedtools list when initializing the agent. Restricting the agent to just getresidentialrates prevents it from pulling irrelevant industrial tariffs.

Index OpenEI utility rates directly into LlamaIndex vector stores to build RAG applications grounded in hard tariff data.

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 LlamaIndex

Create your Vinkius account to connect OpenEI to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Vectorize utility structures with LlamaIndex

`get_utility_detail` and `list_utilities` pull massive amounts of company data that your application indexes for semantic search. Instead of querying an API every time a user asks about a utility, you build a local knowledge base of service territories. This gives your RAG pipeline instant access to generation mixes and contact info. Finding the right company is just a matter of running `search_utilities_by_name` and vectorizing the results. The agent cross-references user queries against the indexed utility IDs. You stop hallucinating company names and start returning actual grid operators.

Query complex rate structures via MCP Server

`get_rate_detail` fetches the granular energy charges, seasonal variations, and taxes that define a specific tariff. LlamaIndex chunks this JSON output and stores it alongside your internal project documents. When a user asks about winter demand charges, the system retrieves the exact math from the vector store. You feed `get_residential_rates` directly into the index to power customer-facing ROI calculators. The agent pulls the tiered pricing structures and combines them with historical usage data. This creates a grounded response based entirely on active utility filings.

Ground location-based energy analysis

`get_rates_by_coordinates` and `get_rates_by_address` map physical locations to specific utility districts. Your LlamaIndex agent takes a user's location, hits the tool, and indexes the available tariffs for that exact spot. The output becomes a permanent part of your searchable project history. For heavy manufacturing sites, `get_industrial_rates` and `get_commercial_rates` pull the complex power factor adjustments required for site selection. You index these heavy-duty tariffs across multiple states to compare operational costs. The RAG system ranks the locations based on the lowest per-kWh industrial rates.

Setup guide

Set up OpenEI MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all OpenEI MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to OpenEI tools.",
)
response = await agent.run("List recent OpenEI data")

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 LlamaIndex

Run `pip install llama-index-tools-mcp` and set up a `BasicMCPClient`. Create an `McpToolSpec`, convert it via `to_tool_list_async()`, and hand it to your `FunctionAgent`.

The framework indexes the JSON responses from tools like `get_utility_rates` into your vector store. You query the indexed data repeatedly without hitting the external API again.

It chunks the tariff structures returned by `get_rate_detail` and embeds them as searchable nodes. Semantic search retrieves only the specific seasonal or demand charges relevant to the user's prompt.

You pass an `allowed_tools` list when initializing the agent. Restricting the agent to just `get_residential_rates` prevents it from pulling irrelevant industrial tariffs.

Latitude and longitude inputs exist only in memory during the execution phase. The MCP Server routes the spatial data to the endpoint, retrieves the local tariffs, and terminates the connection. Vinkius enforces strict ephemeral processing inside an isolated 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