MCP server that helps AI agents pick the lowest-carbon cloud region for a workload.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add eco-router-mcp -- npx -y eco-router-mcp{
"mcpServers": {
"eco-router-mcp": {
"command": "npx",
"args": ["-y", "eco-router-mcp"]
}
}
}MCP Servers overview
# Eco Router MCP
An [MCP](https://modelcontextprotocol.io) server that helps AI agents pick the
lowest-carbon cloud region for a workload.
The same GPU job can emit several times more CO₂ depending on which grid powers
the datacenter. Eco Router maps AWS, Google Cloud and Azure regions to the
electricity grids they draw from, so an agent can ask:
> "Where should I run this training job? Data must stay in the EU and latency
> should be under 150 ms."
and get back a ranked shortlist with the reasoning behind it.
Carbon figures are location-based grid averages. They describe the grid that
supplies each region, not the renewable energy a provider buys, so regions in
the same grid get the same value. See [what the numbers represent](docs/methodology.md#what-the-carbon-numbers-represent).
> **Status: early release (v0.1).** Corrections and feedback are welcome in
> [issues](https://github.com/stevensu04/eco-router-mcp/issues). See
> [Roadmap](#roadmap).
## Install
Requires Node.js 22 or later.
**Claude Code**
```bash
claude mcp add eco-router -- npx -y eco-router-mcp
```
**Claude Desktop** (`claude_desktop_config.json`)
```json
{
"mcpServers": {
"eco-router": {
"command": "npx",
"args": ["-y", "eco-router-mcp"],
"env": { "ELECTRICITY_MAPS_API_TOKEN": "optional" }
}
}
}
```
### Live grid data (optional)
Out of the box, Eco Router uses annual averages (per grid in the US, per
province in Canada, per country elsewhere), so it works with no setup. For hourly, grid-level data, set `ELECTRICITY_MAPS_API_TOKEN` to your
own [Electricity Maps](https://www.electricitymaps.com/) API token. Zones your
plan does not cover fall back to the annual average automatically.
Your use of live data is governed by your own Electricity Maps plan and its
[terms](https://help.electricitymaps.com/en/articles/11750446-terms-of-service).
At the time of writing, Electricity Maps offers free access for academic and
personal non-commercial use, and a 14-day trial for commercial evaluation.
Commercial use requires a paid license. Eco Router does not provide or share
any token.
## Tools
| Tool | What it does |
|---|---|
| `rank_regions` | Ranks regions by grid carbon intensity, optionally balanced against estimated latency from an `origin`. Supports `providers`, `countries`, `maxLatencyMs`, `maxCarbonIntensity`, `carbonWeight`, `energyKwh` and `limit`. |
| `find_clean_window` | For flexible batch jobs, finds the start time in the next 72 hours with the lowest forecast carbon intensity in each grid zone, and the savings compared with starting now. Requires `ELECTRICITY_MAPS_API_TOKEN` with forecast access. |
| `list_regions` | Lists cloud regions and the grid zone each one draws power from. Filter by `provider` (`aws`, `gcp`, `azure`) or `country`. |
`countries` accepts ISO 3166-1 alpha-2 codes and the groups `EU` and `EEA`.
Example request to `rank_regions`:
```json
{
"countries": ["EU"],
"origin": { "lat": 50.11, "lon": 8.68 },
"maxLatencyMs": 40,
"energyKwh": 500
}
```
Example request to `find_clean_window` for a 6-hour job that must finish within
two days:
```json
{
"countries": ["DE", "FR", "SE"],
"durationHours": 6,
"withinHours": 48,
"energyKwh": 500,
"timezone": "Australia/Brisbane"
}
```
Scoring, data sources and their limits are explained in
[docs/methodology.md](docs/methodology.md).
How regions are mapped to grids, and which mappings rest on assumptions, is
documented in [docs/regions.md](docs/regions.md).
## Roadmap
- [x] MCP server skeleton over stdio
- [x] Full AWS, Google Cloud and Azure region dataset with sources
- [x] Carbon data: published annual averages by default, live data with an
optional Electricity Maps API token
- [x] `rank_regions`: rank regions by carbon intensity and estimated latency,
with hard limits such as allowed countries or a carbon ceiling
- [x] US grid-level annual data without a token (EPA eGRID)
- [x] Canadian provincial annual data without a token (National Inventory Report)
- [ ] Grid-level annual data for Australia
- [x] Time shifting: suggest when to run, using carbon forecasts
- [x] Publish to npm and the MCP Registry
## Development
```bash
npm install
npm test # unit tests, no network needed
npm run typecheck
npm run build # compiles to dist/
npm run dev # runs the server over stdio from source
npm run update:baseline # refreshes national averages from Ember
npm run update:egrid # refreshes US grid averages from EPA eGRID
npm run update:canada # refreshes Canadian provincial averages
```
## Data sources
- Annual carbon intensity: [Ember, Yearly Electricity Data](https://ember-energy.org/data/yearly-electricity-data/),
licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
- US grid generation mix: [US EPA eGRID](https://www.epa.gov/egrid) (public domain),
converted to lifecycle emissions with Ember's US factors.
- Canadian provincial generation mix: Environment and Climate Change Canada,
[National Inventory Report, Annex 7](https://data-donnees.az.ec.gc.ca/data/substances/monitor/canada-s-official-greenhouse-gas-inventory/),
converted to lifecycle emissions with Ember's Canadian factors. Contains
information licensed under the
[Open Government Licence – Canada](https://open.canada.ca/en/open-government-licence-canada).
- Live carbon intensity (optional): Source: [ElectricityMaps.com](https://www.electricitymaps.com/),
using your own API token and subject to the terms of your plan.
- Region lists: official AWS, Google Cloud and Azure documentation. See
[docs/regions.md](docs/regions.md).
## Contributing
Corrections to region data are especially welcome. See
[CONTRIBUTING.md](CONTRIBUTING.md) to get started.
## Credits
Eco Router started as a hackathon project. Thanks to the original team for the
scoring design this project builds on: Chris ([@chrislee021225](https://github.com/chrislee021225)), Joli ([@L-Joli](https://github.com/L-Joli)),
Bob ([@Loic0927](https://github.com/Loic0927)), Irene Tsai ([@YunTong09](https://github.com/YunTong09))
and Steven Su ([@stevensu04](https://github.com/stevensu04)).
## License
[MIT](LICENSE)
What people ask about eco-router-mcp
What is stevensu04/eco-router-mcp?
+
stevensu04/eco-router-mcp is mcp servers for the Claude AI ecosystem. MCP server that helps AI agents pick the lowest-carbon cloud region for a workload. It has 1 GitHub stars and its last recorded update is dated 2026-09-17.
How do I install eco-router-mcp?
+
You can install eco-router-mcp by cloning the repository (https://github.com/stevensu04/eco-router-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is stevensu04/eco-router-mcp safe to use?
+
Our security agent has analyzed stevensu04/eco-router-mcp and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains stevensu04/eco-router-mcp?
+
stevensu04/eco-router-mcp is maintained by stevensu04. The last recorded GitHub activity is dated 2026-09-17, with 5 open issues.
Are there alternatives to eco-router-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy eco-router-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/stevensu04-eco-router-mcp)<a href="https://claudewave.com/repo/stevensu04-eco-router-mcp"><img src="https://claudewave.com/api/badge/stevensu04-eco-router-mcp" alt="Featured on ClaudeWave: stevensu04/eco-router-mcp" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ
The fastest path to AI-powered full stack observability, even for lean teams.