How to Use the OpenEI MCP in Claude Code

Q: Can I pipe data from a file to Claude Code to run batch OpenEI lookups?

Yes. That's a primary use case. You can use xargs or a simple while read loop in a shell script to read addresses from a file and pass them to the getratesbyaddress tool.

Q: What's the command to connect Claude Code to the OpenEI MCP server?

Run claude mcp add --transport http openei-mcp -- , replacing with the endpoint provided by Vinkius. Use claude mcp list to confirm it's connected.

Pipe live US electricity rates from OpenEI into any script, cron job, or CI/CD pipeline using Claude Code and this 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 Claude Code

Create your Vinkius account to connect OpenEI to Claude Code — 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Script Bulk Rate Lookups

This isn't for single lookups. Feed a CSV of addresses to a shell script. Your script calls `claude mcp openei-mcp get_rates_by_address` for each line and pipes the structured JSON output to another file. It's that simple. You can process thousands of locations for a feasibility study without ever leaving the terminal. The output is clean JSON, so you can easily parse it with `jq` or any other command-line tool to build your reports.

Automate Tariff Monitoring

Utilities change their rates. Set up a cron job to monitor them. Have it run a daily script that calls `get_rate_detail` with a specific tariff ID you're tracking. Your script can then `diff` the output against yesterday's result. If anything changes—a new demand charge, a shift in TOU hours—you can trigger an alert, send an email, or page an on-call engineer. It's set-and-forget monitoring for critical project inputs.

Test Energy Apps in CI/CD with Claude Code

Don't let your energy modeling app break because a utility changed its rate structure. Integrate this MCP Server into your CI/CD pipeline. Before every deployment, have your GitHub Action run tests that use `get_utility_rates` to pull live data for key service areas. If your application's parser fails on the current, real-world data structure, the build fails. This catches regressions and integration issues before they hit production, ensuring your models are always working with valid data.

Setup guide

Set up OpenEI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see openei-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest OpenEI transactions." It will automatically discover and invoke the available OpenEI tools.

Terminal

claude mcp add --transport http openei-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the OpenEI MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "openei-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

In your workflow YAML file, add a step to install Claude Code and add the OpenEI server credentials. Then you can run commands like `claude mcp openei-mcp get_utility_rates --address '...' | jq .` to use live data in your integration tests.

Yes. That's a primary use case. You can use `xargs` or a simple `while read` loop in a shell script to read addresses from a file and pass them to the `get_rates_by_address` tool.

Run `claude mcp add --transport http openei-mcp -- `, replacing `` with the endpoint provided by Vinkius. Use `claude mcp list` to confirm it's connected.

The data is as fresh as OpenEI's last database update. It's excellent for programmatic access and initial analysis, but be aware there can be a delay from when a utility officially files a rate change. For final underwriting, cross-reference with the utility directly.

Only the arguments for the tool you invoke are sent—for instance, the coordinates for `get_rates_by_coordinates`. The connection is a standard HTTPS request to your Vinkius MCP endpoint, which then securely proxies the request. Nothing else from your terminal or environment is transmitted.

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