How to Use the Ember Climate MCP in Claude Code

Q: Can I pipe data from the Ember Climate MCP server with Claude Code?

Yes, that's what it's designed for. The claude mcp exec command prints raw JSON to stdout, so you can pipe it directly to tools like jq for filtering or tee to save to a file.

Q: What's the most efficient tool for comparing multiple countries?

Use getgenerationmultientity. It lets you pass a comma-separated list of country codes, like entitycode="US,DE,JP", and get all the data back in one API call. It's much faster than calling the single-entity tool in a loop.

Q: How do I add the Ember Climate server to Claude Code?

Run the claude mcp add command with the server URL provided by Vinkius. It's a one-time setup that stores the configuration in your local /.claude.json file.

Pipe global energy data right into your shell scripts. Connect Claude Code to Ember Climate for automated reporting and CI/CD checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ember Climate MCP to Claude Code

Create your Vinkius account to connect Ember Climate to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Ember Climate with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Your ESG Reporting

Set up a cron job that runs a simple shell script. The script uses Claude Code to call `get_power_sector_emissions_yearly` for your countries of interest. The JSON output gets piped straight to `jq` to format a report. That report can then be sent to a Slack channel or an internal dashboard. You can build a fully automated, auditable emissions tracking system in a few lines of bash. It's that direct.

Build Guardrails into Your CI/CD

Your CI pipeline can do more than just run linters. Add a step in your GitHub Action that uses Claude Code and this MCP server to check facts about the world. For instance, you can fail a build if a portfolio change would increase exposure to high-emission energy sources. A simple call to `get_carbon_intensity_yearly` can act as a policy check. If the numbers for a region are trending the wrong way, your pipeline stops the process automatically. This moves compliance from a spreadsheet to your code.

Compose Tools in the Terminal

The Ember Climate tools work like any other command-line utility. You can pipe the output from one command into another. For example, use `get_api_options` to find all valid country codes, then pipe that list into a script that calls `get_electricity_demand_yearly` for each one. This composability is the whole point of the command line. This MCP server simply makes a massive global dataset available as another tool in your `PATH`.

Setup guide

Set up Ember Climate 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 ember-climate-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http ember-climate-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 Ember Climate 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": {
    "ember-climate-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 Ember Climate. 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 Ember Climate 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 Ember Climate MCP in Claude Code

In your workflow YAML file, add a step to install Claude Code and configure the MCP server. Then you can run commands like `claude mcp exec ember-climate-mcp get_power_sector_emissions_yearly --entity US --start_date 2022` and use the output in subsequent steps.

Yes, that's what it's designed for. The `claude mcp exec` command prints raw JSON to stdout, so you can pipe it directly to tools like `jq` for filtering or `tee` to save to a file.

Use `get_generation_multi_entity`. It lets you pass a comma-separated list of country codes, like `entity_code="US,DE,JP"`, and get all the data back in one API call. It's much faster than calling the single-entity tool in a loop.

Run the `claude mcp add` command with the server URL provided by Vinkius. It's a one-time setup that stores the configuration in your local `~/.claude.json` file.

The server doesn't see your code or environment. It only receives the specific data query, which contains things like country names or date ranges. The connection itself is authenticated via a single Vinkius token, and the execution happens in a dedicated, temporary sandbox that's destroyed afterward.

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