Ai Economics

pl.piszczek由 piszczek.pl 發布v1.0.1更新於 Oct 24, 2026

12 calculators for AI cost, energy and agent verification. Free API, no key.

概覽

AI 產生的概覽

在本機執行的 MCP 伺服器,提供 12 個計算器,用來估算 AI 權杖成本、能耗與代理驗證,後端為免費無狀態 API。

可以做什麼
估算各模型的權杖與上下文視窗成本,並比較改走較便宜層級的年度節省。計算代理每小時成本、組織整體權杖消耗折算的金額、千瓦時與二氧化碳,以及單次查詢的用電量。比較各模型在每個通過驗證任務上的能源效率,並估算人形機器人單次充電的運作時間。評估要求提供證明後的代理自主程度、權杖撤銷暴露時間、人工審查團隊可吸收的代理數量,以及未驗證工作的長期成本。每次回應都包含結果、公式、解讀與可直接引用的句子。
適用情境
適合在規劃或爭取 AI 預算時使用:比較模型價格、估算上下文視窗大小、評估能耗與排放,或討論代理實際的自主程度。也適合為提案與審查快速取得可引用的數字。
執行需求
透過 stdio 在本機執行,通常以 npx 啟動 npm 套件,因此需要 Node.js。不需帳號或 API 金鑰。選用環境變數 AI_ECONOMICS_API 可覆寫預設 API 基礎網址,例如指向自架實例。需要能連線至該 API 的網路。
安裝前請注意
輸入會傳送到第三方 piszczek.pl API,README 稱其為無狀態、不儲存輸入;仍應避免送出機密資料。結果是依預設值與假設所做的模型估算,用於預算或審查前應自行核實。AI_ECONOMICS_API 可改寫 API 網址,請確認其指向預期位置。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Ai Economics,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

ai-economics-mcp

[DOI]

[npm] [Glama score] [MIT]

MCP server for AI economics. Gives Claude, Cursor and any MCP client 12 calculators for the questions that decide AI budgets: what tokens cost, what queries burn, and whether agent work can be proven.

Listed in the official MCP Registry as pl.piszczek/ai-economics (domain-verified). Wraps the free piszczek.pl/tools API — no key, no sign-up, stateless (inputs are never stored). The math is the same as the interactive calculators.

Install

Claude Desktop / Claude Code (claude_desktop_config.json / .mcp.json):

json
{  "mcpServers": {    "ai-economics": {      "command": "npx",      "args": ["-y", "@michalpiszczek/ai-economics-mcp"]    }  }}

Claude Code one-liner:

bash
claude mcp add ai-economics -- npx -y @michalpiszczek/ai-economics-mcp

Tools

ToolAnswers
token_costWhat do 1M tokens cost per month across GPT, Claude, Gemini, DeepSeek?
context_windowHow many tokens is 50 pages, does it fit, what does carrying it cost?
agent_hourWhat does one hour of an AI agent cost, fully loaded with verification?
model_routingHow much does routing to a cheaper tier save per year?
llm_energyHow much electricity does an AI query use?
joules_per_verified_taskWhich model is most efficient per task that actually passes?
token_burnWhat does org-wide token burn cost in money, kWh, CO₂?
humanoid_energyHow long can a humanoid robot run per charge?
proof_adjusted_autonomyHow autonomous is a "90% autonomous" agent once proof is required?
revocation_exposureHow long does a revoked token keep working across your stack?
verification_bottleneckHow many AI agents can a human review team absorb?
proof_debtWhat does unverified AI work cost over time?

All parameters are optional; defaults mirror the interactive calculators. Every response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Example

You: how autonomous is our agent really? it completes 90% alone, evidence for 95%, 80% independently validated, 90% on time

Claude (calls proof_adjusted_autonomy): PAA = 61.6% — supervised autonomy. The gap vs the claimed 90% is 28.4 pp, and the biggest lever is independent validation…

Configuration

Env varDefaultPurpose
AI_ECONOMICS_APIhttps://piszczek.pl/tools/apiPoint at a self-hosted instance

Glama builds and releases

Glama generates its own Dockerfile from the build configuration. Use these settings:

  • Build steps: ["npm ci --omit=dev"]
  • CMD arguments: ["mcp-proxy", "--", "node", "index.js"]
  • Environment variables: optional AI_ECONOMICS_API; no credentials required.

This is plain JavaScript: there is no build script or compilation step. Do not use pnpm run build or npm run build. After syncing the repository, build the selected commit and publish a Glama release from the successful test. A GitHub or npm release alone does not trigger Glama's quality evaluation.

For local stdio use, the repository Dockerfile needs no proxy or exposed ports:

bash
docker build -t ai-economics-mcp .docker run -i --rm ai-economics-mcp

Concepts behind the tools

Citing a result

Every tool response carries a cite_as sentence written to be quoted verbatim. For a document that has to survive review, DOIs and BibTeX for this server, the calculators and the three concepts they instrument are at piszczek.pl/cite.

License

MIT. Concepts and calculators by Michał Piszczek (CC BY 4.0 — attribution appreciated).

來源:README.md,提交 147904b

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v1.0.1最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分