MCP App Store
by KeenEthics
Carbon of Compute icon

Carbon of Compute MCP Server for Claude and ChatGPT

By REEL LCI

Overview

Carbon of Compute estimates the greenhouse gas and water footprint of running AI language models, per 1,000 output tokens or per task. Each figure is split into four parts: the electricity the hardware draws, the manufacturing of that hardware spread over its working life, the datacenter facility plant, and optionally a share of model training. Footprint results come with low and high values. Ask for one model's footprint, compare models under the same assumptions, or change the grid region, datacenter efficiency (PUE), hardware lifetime, utilization and cooling regime. The connector also returns the manufacturing footprint of AI accelerators (NVIDIA H100, H200, B200, A100, AMD MI300X) split into logic die, HBM memory, package and board, an 8-GPU server line by line, and datacenter facility factors from manufacturer EPDs. Footprint and ranking answers link to the same view on carbonofcompute.com and to the method report. Hardware manufacturing is built on REEL LCI, a life cycle inventory of electronics manufacturing whose foreground inventory comes from public sources, linked to licensed ecoinvent 3.12 background data. Figures are estimates from public evidence for a reference deployment, not a provider's own measurement. The connector only reads published data. It needs no account and takes no actions.

How to connect

  1. Claude: Open the Carbon of Compute listing in the Claude connectors directory and choose Connect. Claude listing Carbon of Compute exposes 8 tools here.
  2. ChatGPT: Open the Carbon of Compute listing in the ChatGPT app directory and choose Connect. ChatGPT listing Carbon of Compute exposes 8 tools here.

Tools

get_accelerator_manufacturing

ChatGPT
Return the cradle-to-gate manufacturing carbon (kgCO2e) and fab water (L) of AI accelerators (NVIDIA H100, H200, B200, A100, AMD MI300X), split into logic die, HBM memory, package and board, with the vendor product carbon footprint where one is published. Also returns the per-GPU-slot values the calculator uses, which add a share of the host server.

get_facility_manufacturing

ChatGPT
Return the datacenter facility factors used by Carbon of Compute: manufacturing carbon of the power chain and cooling plant (a line-item bill of materials anchored to manufacturer EPDs), standby generator fuel, refrigerant leakage, and on-site water use by cooling regime, each per kWh of IT energy. The building shell is excluded.

get_methodology

ChatGPT
Return a short summary of how Carbon of Compute estimates AI footprints: the four parts counted, the functional unit, the default assumptions, what is left out, and links to the full method report. Use it to explain or caveat a number.

get_model_footprint

ChatGPT
Return the full-stack carbon (gCO2e) and water (mL) footprint of one AI model, split into operational electricity, hardware manufacturing, facility plant and optional training, with low and high values. Also returns energy per unit and a link to the same view on carbonofcompute.com. Defaults match the site: US average grid, PUE 1.15, 5-year hardware life, 33% busy time, training excluded, per 1,000 output tokens. The low-high span is not complete uncertainty; check deployment differences before using a figure in an emissions inventory.

get_server_manufacturing

ChatGPT
Return the manufacturing carbon (kgCO2e) of an 8-GPU NVIDIA H100 AI server line by line: CPUs, system memory, network cards, circuit boards, power supplies, chassis, NVSwitch, network fabric share, storage and the eight accelerators. Also returns host-silicon fab water.

list_models

ChatGPT
List the AI language models in the Carbon of Compute catalogue, with provider, open or closed weights, evidence level (measured, derived or estimated), whether it is a reasoning model, and the hardware assumed. Use it to find the model id for get_model_footprint. Optional filters narrow the list.

list_scenario_options

ChatGPT
List the values accepted by the scenario inputs of get_model_footprint and rank_models: grid regions with their carbon intensity, datacenter PUE profiles, cooling regimes, accelerator options, hardware lifetimes, busy-time scenarios, training options and workload presets.

rank_models

ChatGPT
Rank AI models by total carbon per unit under one set of assumptions, lowest first, as the carbonofcompute.com leaderboard does. Can be limited to a list of models to compare, or filtered by weights, evidence level or provider. Each row has the total, its low-high range and the split into operational, hardware manufacturing, facility and training.

get_accelerator_manufacturing

Claude
Return the cradle-to-gate manufacturing carbon (kgCO2e) and fab water (L) of AI accelerators (NVIDIA H100, H200, B200, A100, AMD MI300X), split into logic die, HBM memory, package and board, with the vendor product carbon footprint where one is published. Also returns the per-GPU-slot values the calculator uses, which add a share of the host server.

get_facility_manufacturing

Claude
Return the datacenter facility factors used by Carbon of Compute: manufacturing carbon of the power chain and cooling plant (a line-item bill of materials anchored to manufacturer EPDs), standby generator fuel, refrigerant leakage, and on-site water use by cooling regime, each per kWh of IT energy. The building shell is excluded.

get_methodology

Claude
Return a short summary of how Carbon of Compute estimates AI footprints: the four parts counted, the functional unit, the default assumptions, what is left out, and links to the full method report. Use it to explain or caveat a number.

get_model_footprint

Claude
Return the full-stack carbon (gCO2e) and water (mL) footprint of one AI model, split into operational electricity, hardware manufacturing, facility plant and optional training, with low and high values. Also returns energy per unit and a link to the same view on carbonofcompute.com. Defaults match the site: US average grid, PUE 1.15, 5-year hardware life, 33% busy time, training excluded, per 1,000 output tokens. The low-high span is not complete uncertainty; check deployment differences before using a figure in an emissions inventory.

get_server_manufacturing

Claude
Return the manufacturing carbon (kgCO2e) of an 8-GPU NVIDIA H100 AI server line by line: CPUs, system memory, network cards, circuit boards, power supplies, chassis, NVSwitch, network fabric share, storage and the eight accelerators. Also returns host-silicon fab water.

list_models

Claude
List the AI language models in the Carbon of Compute catalogue, with provider, open or closed weights, evidence level (measured, derived or estimated), whether it is a reasoning model, and the hardware assumed. Use it to find the model id for get_model_footprint. Optional filters narrow the list.

list_scenario_options

Claude
List the values accepted by the scenario inputs of get_model_footprint and rank_models: grid regions with their carbon intensity, datacenter PUE profiles, cooling regimes, accelerator options, hardware lifetimes, busy-time scenarios, training options and workload presets.

rank_models

Claude
Rank AI models by total carbon per unit under one set of assumptions, lowest first, as the carbonofcompute.com leaderboard does. Can be limited to a list of models to compare, or filtered by weights, evidence level or provider. Each row has the total, its low-high range and the split into operational, hardware manufacturing, facility and training.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/carbon-of-compute"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/carbon-of-compute)