AI Footprint
Water and energy footprint of AI use: chat prompts, agent sessions, methodology and sources.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"ai-footprint": {
"url": "https://prompt-tightener-production.up.railway.app/mcp"
}
}
}遠端端點
https://prompt-tightener-production.up.railway.app/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢estimate_ai_footprint(queries_per_day, usage, boundary, days)
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.
輸入結構描述
{
"type": "object",
"properties": {
"queries_per_day": {
"title": "Queries Per Day",
"type": "number"
},
"usage": {
"default": "simple",
"enum": [
"simple",
"mixed",
"intensive"
],
"title": "Usage",
"type": "string"
},
"boundary": {
"default": "comprehensive",
"enum": [
"onsite",
"comprehensive"
],
"title": "Boundary",
"type": "string"
},
"days": {
"default": 1,
"title": "Days",
"type": "integer"
}
},
"required": [
"queries_per_day"
],
"title": "estimate_ai_footprintArguments"
}🟢get_methodology
Return the per-prompt energy and water figures, accounting boundaries, sources, limitations, a citation line, and why published AI water estimates differ by ~100x (0.3 mL to 50 mL per prompt). Call this before explaining or citing any AI water figure.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "get_methodologyArguments"
}🟢compare_water_use(water_ml)
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.
輸入結構描述
{
"type": "object",
"properties": {
"water_ml": {
"title": "Water Ml",
"type": "number"
}
},
"required": [
"water_ml"
],
"title": "compare_water_useArguments"
}🟢estimate_session_footprint(input_tokens, output_tokens, cached_input_tokens, model_class, boundary)
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.
輸入結構描述
{
"type": "object",
"properties": {
"input_tokens": {
"title": "Input Tokens",
"type": "integer"
},
"output_tokens": {
"title": "Output Tokens",
"type": "integer"
},
"cached_input_tokens": {
"default": 0,
"title": "Cached Input Tokens",
"type": "integer"
},
"model_class": {
"default": "frontier",
"enum": [
"small",
"frontier",
"reasoning"
],
"title": "Model Class",
"type": "string"
},
"boundary": {
"default": "comprehensive",
"enum": [
"onsite",
"comprehensive"
],
"title": "Boundary",
"type": "string"
}
},
"required": [
"input_tokens",
"output_tokens"
],
"title": "estimate_session_footprintArguments"
}社群
證據