How to Use the Electricity Maps Carbon Intelligence MCP in OpenAI Agents SDK

Q: How do I connect the Electricity Maps Carbon Intelligence MCP Server to OpenAI Agents SDK?

Initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint. Pass that directly to the mcpservers array in your Agent constructor. The SDK handles the rest automatically.

Route production workloads to green grids automatically using OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Electricity Maps Carbon Intelligence MCP to OpenAI Agents SDK

Create your Vinkius account to connect Electricity Maps Carbon Intelligence to OpenAI Agents SDK 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 Electricity Maps Carbon Intelligence with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce carbon limits with OpenAI Agents SDK

This MCP Server exposes the `get_carbon_intensity` tool to pull live emissions data directly into your agent runtime. You pass a zone code like US-CA, and the endpoint returns the exact grams of CO2 equivalent per kilowatt-hour currently generated on that grid. This setup thrives inside your production environment. You define strict guardrails that block compute jobs if the local grid intensity spikes above a hard threshold. Your agent checks the metric, evaluates the rule, and either executes the workload or shifts it to a cleaner region while the OpenAI dashboard traces the entire decision tree.

Analyze grid generation mixes

Agents trigger the `get_power_production_breakdown` tool to see exactly what physical infrastructure is feeding a specific zone right now. The response splits out the precise percentages of nuclear, wind, solar, and fossil fuels currently active on that local grid. Handoffs make this data actionable without writing complex routing logic. One specialized analyst agent pulls the breakdown, spots a massive surplus in wind generation, and passes the context over to an infrastructure agent. That second agent then spins up heavy batch processing tasks to consume the cheap power before the weather shifts.

Map global energy infrastructure

Running the `list_energy_zones` tool returns the complete index of supported geographical regions and their corresponding API codes. Your AI client needs this catalog to know which physical locations it can actually query for power metrics. Wiring this up requires zero manual tool definitions. You pass the endpoint via `MCPServerStreamableHttp` into your agent constructor, and the SDK auto-discovers the routing functions. Setting `cacheToolsList=True` keeps your initialization times flat even as the region map expands.

Setup guide

Set up Electricity Maps Carbon Intelligence MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Electricity Maps Carbon Intelligence tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Electricity Maps Carbon Intelligence tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Electricity Maps Carbon Intelligence tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Electricity Maps Carbon Intelligence Agent",
            instructions="You have access to Electricity Maps Carbon Intelligence tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Electricity Maps. 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 Electricity Maps Carbon Intelligence 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 Electricity Maps Carbon Intelligence MCP in OpenAI Agents SDK

Initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass that directly to the `mcp_servers` array in your Agent constructor. The SDK handles the rest automatically.

Yes. You write a guardrail rule that evaluates the output from the intensity tool. If the value crosses your defined limit, the agent fires off an alert or halts the deployment pipeline.

It fits perfectly into multi-agent setups. An analyst agent fetches the production breakdown and passes the raw metrics to a deployment agent that decides where to spin up containers.

Direct calls require hardcoding endpoints and writing custom parsing logic. Connecting this MCP Server gives your agents native access to the functions without you writing a single line of boilerplate code.

The server only touches geographical zone codes and grid coordinates. Your proprietary application data, user prompts, and agent reasoning traces never leave your infrastructure or enter the Vinkius 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