How to Use the OpenEI MCP in Mastra AI

Q: How do I add OpenEI tools to a Mastra AI agent?

Instantiate the MCPClient with your Vinkius MCP endpoint and fetch the tool list. You then spread those tools directly into your agent's configuration object so it can query tariffs autonomously.

Q: Does Mastra AI support human-in-the-loop validation for OpenEI data?

Yes, you can enable requireToolApproval on tools like getratedetail. This pauses the execution path on the MCP Server and requires an operator to confirm the retrieved tariff details before the agent proceeds.

Build resilient, multi-step energy workflows with Mastra AI and the OpenEI MCP server.

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 Mastra AI

Create your Vinkius account to connect OpenEI to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate complex tariff lookups with Mastra AI

The `get_utility_rates` tool fetches location-specific electricity tariffs and feeds them directly into your Mastra AI workflows. When a rate query fails due to local API limits, the workflow engine automatically retries with exponential backoff. This ensures your automated energy audits never stall due to temporary network hiccups. You register this MCP Server by instantiating the `MCPClient` and spreading the tools into your agent definition. From there, your agent can autonomously decide whether to pull residential, commercial, or industrial rates based on the incoming lead data.

Enforce human-in-the-loop approvals for solar bids

The `get_rate_detail` tool extracts exhaustive tariff structures including demand charges and seasonal variations. Because pricing models can make or break a commercial solar deal, you can use Mastra's `requireToolApproval` feature before generating a final proposal. Your team gets a chance to verify the tariff details before the agent sends the contract. This guardrail prevents automated systems from quoting incorrect energy savings. The workflow pauses, alerts a human reviewer, and resumes only after the data is verified.

Route utility queries dynamically using GPS data

The `get_rates_by_coordinates` tool maps latitude and longitude coordinates to the exact serving utility. Mastra's conditional branching lets your agent run secondary lookups like `get_utility_detail` only if the initial coordinate query returns an active provider. If the coordinates land outside serviced territories, the workflow branches to notify your operations team. This programmatic logic eliminates manual data entry errors. Your agent handles the entire lookup pipeline without hardcoded routing scripts.

Setup guide

Set up OpenEI MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All OpenEI tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "openei-mcp-client",
  servers: {
    "openei-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "OpenEI Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to OpenEI tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent OpenEI transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the `MCPClient` with your Vinkius MCP endpoint and fetch the tool list. You then spread those tools directly into your agent's configuration object so it can query tariffs autonomously.

Yes, the framework has a built-in workflow engine that supports automatic retries. If `get_commercial_rates` hits an API limit, the system pauses and retries using exponential backoff.

Yes, you can enable `requireToolApproval` on tools like `get_rate_detail`. This pauses the execution path on the MCP Server and requires an operator to confirm the retrieved tariff details before the agent proceeds.

The client automatically detects the Server-Sent Events transport when connecting to your Vinkius endpoint. This ensures a stable, persistent connection for long-running workflow steps.

All tariff data and coordinate payloads are routed through encrypted TLS channels directly to the isolated V8 sandbox on Vinkius. Your query parameters are processed in memory and wiped immediately after execution, leaving zero footprint.

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