GreenCalculus
Sourced carbon emission factors + audit-traced calculations an AI can cite.
README
GreenCalculus MCP server
Sourced greenhouse-gas emission factors and audit-traced carbon calculations, as an MCP server. Every value comes back with its exact source cell and a pinned data version — so an agent hands back a number a person can cite and a machine can reproduce, instead of a guess.
Do you need this package?
Probably not. The server is remote, and if your client speaks remote MCP you should point it straight at the URL — nothing to install, nothing to update:
{
"mcpServers": {
"greencalculus": {
"url": "https://mcp.greencalculus.com",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}
This package exists for the clients that can only spawn a local stdio process, and for docker run installs. It is a thin bridge: it forwards each JSON-RPC message to the remote server and returns the reply verbatim. No method is special-cased, so new tools appear here without a release.
Use it over stdio
{
"mcpServers": {
"greencalculus": {
"command": "npx",
"args": ["-y", "greencalculus-mcp"],
"env": { "GREENCALCULUS_API_KEY": "YOUR_KEY" }
}
}
}
Or with Docker — -i is required and -t must be omitted, because the container's stdin/stdout are the transport and a TTY corrupts the stream:
{
"mcpServers": {
"greencalculus": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "GREENCALCULUS_API_KEY", "greencalculus/mcp"],
"env": { "GREENCALCULUS_API_KEY": "YOUR_KEY" }
}
}
}
Get a free key at https://greencalculus.com/developers — no card. Discovery (initialize, tools/list) works without one; calling a tool needs it.
Tools
| Tool | What it does |
|---|---|
lookup_factor |
Fetch one emission factor by key, with its source and version |
search_factors |
Search the corpus by free text |
resolve_factor |
Map a messy real-world description to the best-matching factor |
explain_absence |
Say why a factor does not exist, rather than returning nothing |
calculate_activity |
Activity → emissions, with unit conversion and GHG Protocol scope |
calculate_electricity |
Location-based and market-based electricity |
calculate_embodied |
Embodied carbon (EN 15978), explicit about missing lifecycle stages |
calculate_pcaf |
PCAF financed emissions, with the audit trail |
calculate_freight |
Freight by mode, distance and load |
calculate_spend |
Spend-based EEIO |
calculate_business_travel |
Business travel across modes |
Configuration
| Variable | Default | Meaning |
|---|---|---|
GREENCALCULUS_API_KEY |
— | Your API key. GC_API_KEY is accepted as an alias; the explicit name wins. |
GREENCALCULUS_MCP_URL |
https://mcp.greencalculus.com |
Override the endpoint. |
GREENCALCULUS_MCP_TIMEOUT_MS |
120000 |
Per-request timeout. |
Diagnostics go to stderr. Nothing but JSON-RPC is ever written to stdout — a stray byte there corrupts the session.
Develop
npm test # unit tests, no network
node bin/greencalculus-mcp.js # reads JSON-RPC on stdin
docker build -t greencalculus/mcp .
Also available
- REST API and docs — https://greencalculus.com/developers
- Client SDKs (Python, JS/TS) — https://github.com/jeremiahsay/greencalculus-sdk
- Official MCP registry —
com.greencalculus/api - Smithery — https://smithery.ai/servers/greencalculus/api
Licence
MIT — see LICENSE. The licence covers this bridge. Emission-factor data returned by the API carries the licence of its underlying source, which is named in every response.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.