MCP server · Developer tools
Eco Router MCP server
by stevensu04
Your AI can pick the lowest-carbon cloud region for a job, ranked by grid carbon and latency.
Eco Router is a helper that lets your AI suggest where to run a cloud job so it produces less carbon. You ask in plain words, and it comes back with a ranked shortlist of cloud regions and the reasons behind the ranking. It is handy if you plan computing work and care about its environmental impact.
What is an MCP server? The 30-second version
On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to a map of cloud regions and the electricity grids that power them, so the AI can look up carbon and latency details for you. Once it is connected, you just ask a normal question and the AI uses this helper behind the scenes.
What this MCP server does
You ask your AI something like where to run a training job with certain limits. The AI passes your question to Eco Router. Eco Router looks at its list of AWS, Google Cloud and Azure regions, matches each one to the electricity grid it uses, and compares carbon intensity and estimated latency. It sends back a ranked shortlist, and your AI explains the result to you in the chat.
What you can do with it
- Rank cloud regions by grid carbon intensity
- Balance carbon against estimated latency from a location you choose
- Limit results to certain countries or to the EU and EEA
- Set a maximum latency or a maximum carbon intensity
- Find the cleanest start time for a batch job in the next 72 hours
- List cloud regions and the grid zone each one draws power from
Try asking your AI
- “Where should I run this training job? Data must stay in the EU and latency should be under 150 ms.”
- “Rank AWS and Google Cloud regions in Germany and France by carbon intensity for a 500 kWh job.”
- “Find the cleanest 6-hour window in the next two days to run this batch job in Germany, France or Sweden.”
- “List Azure regions in the EU and tell me which grid each one uses.”
What it gives back to you
You get a ranked list of cloud regions, each with its carbon intensity and estimated latency, plus the reasoning behind the order. For time shifting, you get a suggested start time and the savings compared with starting now. Your AI shows this as a short list or a small table in the chat, so you can compare options at a glance.
Before you start
What you need
- Node.js 22 or later
- The Claude desktop app or Claude Code, if you want to add it there
- Optional: an Electricity Maps API token for live data and forecasts (a kind of password for apps; the site gives you one, and free access is limited to academic and personal non-commercial use)
Good to know
The carbon numbers are location-based grid averages, so they describe the grid that supplies each region, not the renewable energy a provider buys, and regions in the same grid get the same value.
Install it with your AI
Add Eco Router MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Eco Router MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.
Who it's for
People who plan cloud computing work, such as developers, data scientists and sustainability or operations teams, and anyone curious about the carbon impact of where a job runs.
