# Emission Factors [Health: Active]

**Category:** 🌳 Environment & Nature  
**Repository:** https://github.com/rozetyp/emission-factors-mcp  
**GitHub Stars:** 1  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/emission-factors

## Description
Keyless US grid carbon + power cost by ZIP: eGRID Scope 2, Scope 1 fuels, site ranking, clean hours

## Tools
Capabilities this server exposes over MCP:

- **lookup_emission_factor** — EPA eGRID CO2e + full generation mix for a ZIP
- **lookup_by_coordinates** — Same, resolved from lat/lon via Census geocoder
- **lookup_batch** — Emission factors for up to 100 ZIPs at once
- **calculate_emissions** — Scope 2 CO2e for a ZIP + kWh, location-based and market-based (Green-e residual mix)
- **hourly_intensity** — Hourly grid carbon intensity (EIA-930, ~24h lag)
- **plant_emissions** — Plant emissions (EPA CAMD): facility summaries or unit-hour records
- **utility_tariff** — Utility-specific tariff, not state average (OpenEI URDB)
- **electricity_rate** — State-average retail rate by sector (EIA-861)
- **compare_sites** — Rank 2-25 candidate sites on grid carbon, $/kWh and cleanest daily window
- **cleanest_hours** — Cleanest N-hour window of the day to run a flexible load, in local time
- **calculate_fuel_emissions** — Scope 1 CO2e for fuels burned on site (EPA GHG Emission Factors Hub)

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "emission-factors": {
    "command": "npx",
    "args": ["-y","github:rozetyp/emission-factors-mcp"],
    "env": {
      "EMISSION_FACTORS_API_BASE": ""
    }
  }
}
```

**Requires environment variables:** `EMISSION_FACTORS_API_BASE` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What Emission Factors does

The Emission Factors MCP server connects MCP clients to the public API at emission-factors.com. It returns US electricity data organized around ZIP codes, with coordinate-based resolution available through the Census geocoder. The underlying sources include EPA eGRID, EIA-861, EIA-930, EPA CAMD, OpenEI URDB, and the GHG Emission Factors Hub.

The Emission Factors MCP server supports both operational analysis and reporting inputs. You can retrieve a ZIP's grid emission factor and generation mix, estimate location-based or market-based Scope 2 emissions, review hourly carbon intensity, and calculate Scope 1 emissions for on-site fuel use. It also supports state-average electricity rates, utility-specific tariffs, plant emissions, candidate-site ranking, and daily clean-hour selection.

This belongs in the Environment & Nature category. It is relevant when an agent needs US location-specific electricity information rather than a general explanation of emissions accounting.

## How it works

The server is a thin MCP proxy. Each tool validates its inputs, calls a corresponding API endpoint, and returns JSON; it does not maintain local state or handle API keys. The hosted endpoint uses Streamable HTTP at `https://emission-factors.com/mcp`. The local package runs as a Node.js process over stdio and proxies the same public API.

Inputs are generally ZIP codes, although some tools accept latitude and longitude, balancing-authority identifiers, facility or state identifiers, utility details, fuel quantities, or arrays of candidate locations. Batch lookup accepts up to 100 ZIP codes. Site comparison accepts between 2 and 25 candidate ZIP codes.

Data timing varies by source. Hourly intensity is based on EIA-930 data with an approximate 24-hour delay. Plant emissions come from EPA CAMD and are published quarterly, with a stated delay of at least 45 days after the quarter. The API also applies server-side caching to several external-data endpoints.

## Setup and configuration

For remote use, configure an MCP client with `https://emission-factors.com/mcp`; authentication and an API key are not required. The README provides setup examples for Claude custom connectors, Claude Code, Cursor, Cline, Continue, and Zed. Claude Desktop's local configuration starts stdio servers, so its `claude_desktop_config.json` is not the remote HTTP setup described here.

For local execution, use Node.js 18 or newer. A client can run the package with `npx -y github:rozetyp/emission-factors-mcp`, or you can clone the repository, run `npm install`, and start `dist/index.js`. The optional `EMISSION_FACTORS_API_BASE` variable changes the API base URL and defaults to `https://emission-factors.com`.

## Tools and capabilities

The Emission Factors MCP server exposes eleven tools:

- `lookup_emission_factor` returns EPA eGRID CO2e data and the generation mix for a ZIP.
- `lookup_by_coordinates` resolves latitude and longitude before returning equivalent data.
- `lookup_batch` retrieves factors for up to 100 ZIP codes.
- `calculate_emissions` calculates location-based and market-based Scope 2 results from ZIP and kWh inputs.
- `hourly_intensity` returns EIA-930 hourly grid intensity for a ZIP or balancing area.
- `plant_emissions` returns EPA CAMD facility summaries or unit-hour records.
- `utility_tariff` retrieves a utility-specific OpenEI URDB tariff.
- `electricity_rate` returns EIA-861 state-average retail rates by sector.
- `compare_sites` ranks candidate sites by grid carbon, electricity cost, and clean daily window.
- `cleanest_hours` identifies a daily local-time window for flexible load.
- `calculate_fuel_emissions` calculates Scope 1 CO2e for specified on-site fuels.

## Limitations and notes

Coverage and timing depend on the source datasets. Plant data covers fossil units above 25 MW, while hourly intensity is intended for timing decisions and uses fixed per-fuel factors on in-balancing-area generation; it is not presented as an inventory-reporting factor. State-average rates are not substitutes for utility-specific tariffs.

The service is anonymous but rate-limited to 2,000 requests per hour per IP. Requests exceeding that limit receive HTTP 429 responses with a retry hint. The project and API are unofficial wrappers around the cited government and NREL/OpenEI sources and are licensed under MIT.

_Full upstream README: https://allmcps.com/mcp/emission-factors/readme_