mcpbeat Sign in

AI Footprint MCP Server

answering

AI Footprint is answering right now. Last checked 4 min ago. It exposes 4 tools. Last commit 16 Oct 2026.

Water and energy footprint of AI use: chat prompts, agent sessions, methodology and sources.

Uptime history 15 days of history
15 days agonow
100.0%
Uptime 24h
183 of 183 checks
4
Tools
read from the server
226 ms
Response time
average over 24h
1
Stars
last commit 16 Oct 2026

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 13 October 2026. No other catalogue keeps this.

13 Oct a tool description was rewritten get_methodology

What the code does

We read the source, 4 d ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Page executes code built at runtime server/widget/widget.html:107
  $('w').innerHTML = w.slice(0, i) + '<small>' + w.slice(i + 1) + '</small>';

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

run in your terminal
claude mcp add ai-footprint --transport http https://prompt-tightener-production.up.railway.app/mcp
Settings → Connectors → Add custom connector, then paste this address
https://prompt-tightener-production.up.railway.app/mcp
~/.codex/config.toml
[mcp_servers.ai-footprint]
url = "https://prompt-tightener-production.up.railway.app/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "ai-footprint": {
      "url": "https://prompt-tightener-production.up.railway.app/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "ai-footprint": {
      "type": "http",
      "url": "https://prompt-tightener-production.up.railway.app/mcp"
    }
  }
}

This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

estimate
estimate_ai_footprint
Estimate the water (mL) and energy (Wh) used by chat-style AI prompts (ChatGPT, Claude, Gemini etc.). queries_per_day: prompts per day. usage: 'simple' (text chat, ~0.34 Wh/prompt), 'mixed' (~1 Wh), 'intensive' (image generation / deep reasoning, ~3 Wh). boundary: 'onsite' (data-centre cooling only, as vendors report) or 'comprehensive' (adds water used to generate the electricity – the wider boundary most researchers use). days: number of days to total over (e.g. 250 workdays, 365). Returns per-prompt, per-day and total figures with everyday equivalents, assumptions and a source link. For agentic/coding sessions use estimate_session_footprint instead.
estimate_session_footprint
Estimate the water and energy of an AI session (e.g. an agent or coding-assistant run) from its token usage. Pass the SUM across all model calls: input_tokens (uncached prompt tokens), output_tokens (including any reasoning/thinking tokens) and cached_input_tokens (prompt-cache reads). model_class: 'small' (Haiku/mini/Flash-class), 'frontier' or 'reasoning'. Returns a central estimate and a 0.3x–3x range – this is an order-of-magnitude estimate calibrated to published per-prompt figures, not a measurement.
compare
compare_water_use
Convert a volume of water (mL) into everyday comparisons: teaspoons, 500 mL bottles, shower time, and lifecycle items (A4 sheet, almond, cup of tea, beef burger), plus the number of typical AI text prompts it equals. Includes the boundary caveat that lifecycle footprints are not like-for-like.
methodology
get_methodology
Return the per-prompt energy and water figures, accounting boundaries, sources, limitations, a citation line, and the reasons published AI water estimates differ by ~100x (0.3 mL to 50 mL per prompt). Use it to explain or check a published AI water or energy figure.

Endpoints

URLTransportStateLatencyChecked
https://prompt-tightener-production.up.railway.app/mcp streamable-http answering 195 ms 4 min ago
https://footprint.pharmatools.ai/mcp streamable-http answering 283 ms 4 min ago

Alternatives to AI Footprint

same job, measured the same way
Octopus Energy (octopus-mcp)
by mattoddie

Octopus Energy usage and costs, tariffs, Agile prices, bills, EV charging and Saving Sessions

local only
MERX - TRON Resource Exchange
by merx

TRON energy exchange for AI agents. 54 tools, 30 prompts, 21 resources. A2A + ACP.

27 installs/wk 66 tools answering
Aidemd MCP
by aidemd-mcp

MCP server that teaches any AI agent the AIDE methodology via progressive disclosure

84 installs/wk local only
WattScope
by com-wattscope

Tracks the estimated carbon footprint of AI model usage, per org and project.

answering
James Prompt
by jamesprompt

AI agent for business strategy and business design — run strategy missions and 15 analyses.

answering
PostgreSQL MCP Server
by neverinfamous

Enterprise PostgreSQL MCP server with 63 tools, 10 resources, 10 prompts for AI-native operations

local only
Formio MCP
by form

Create and manage Form.io forms, resources, actions, roles, and projects from your AI agent.

304 installs/wk local only
Macbeth
by wende

Open-source computer use for macOS agents.

12 installs/wk local only

AI Footprint — questions

Answers built from our own checks of this server.

What can AI Footprint do?
It exposes 4 tools, read directly from the server on our last check. Among them: compare_water_use, estimate_ai_footprint, estimate_session_footprint, get_methodology. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is AI Footprint working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 183 of 183 checks got a reply (100.0%), average response time 226 ms. The bar chart above shows every period we have measured.
How do I connect AI Footprint?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AI Footprint need an API key?
No. AI Footprint completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AI Footprint?
It answers our handshake in 226 ms on average, which is faster than 72% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is AI Footprint open source?
The code is open source: it is published under the MIT licence, written in Python and 1 stars on GitHub. The licence covers the code in the repository, not the hosted service at prompt-tightener-production.up.railway.app, which runs on its operator's own terms.