Ai Economics

pl.piszczek由 piszczek.pl 发布v1.0.1更新于 Oct 24, 2026

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

已验证STDIO仅桌面金融数据与分析AI 与机器学习

概览

AI 生成的概览

本地运行的 MCP 服务器，提供 12 个计算器，用于估算 AI 令牌成本、能耗与智能体验证，后端为免费无状态 API。

可以做什么
估算各模型的令牌与上下文窗口成本，并比较路由到更便宜档位的年度节省。计算智能体每小时成本、组织级令牌消耗折算的金额、千瓦时与二氧化碳，以及单次查询的耗电量。比较各模型在每个通过验证的任务上的能效，并估算人形机器人单次充电的运行时长。评估要求提供证据后的智能体自主度、令牌吊销暴露时长、人工审核团队可承接的智能体数量，以及未验证工作的长期成本。每次响应都包含结果、公式、解读和可直接引用的句子。
适用场景
适合在规划或论证 AI 预算时使用：比较模型价格、估算上下文窗口大小、评估能耗与排放，或讨论智能体实际自主程度。也适合为提案和评审快速取得可引用的数字。
运行要求
通过 stdio 在本地运行，通常用 npx 启动 npm 包，因此需要 Node.js。无需账号或 API 密钥。可选环境变量 AI_ECONOMICS_API 可覆盖默认 API 基础地址，例如指向自建实例。需要能访问该 API 的网络。
安装前请注意
输入会发送到第三方 piszczek.pl API，README 称其无状态、不存储输入；仍应避免提交机密数据。结果是基于默认值和假设的模型估算，用于预算或评审前应自行核实。AI_ECONOMICS_API 可改写 API 地址，请确认其指向预期位置。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Ai Economics，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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).

来源：README.md，提交 147904b

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v1.0.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分