About ai-economics
ai-economics is an MCP server for AI budgeting and agent verification, with 12 calculators for cost, energy, and autonomy. It calls a free API without a key, stores no inputs, and returns formulas and citation-ready text.
Key features
- 01Calculate model token costs
- 02Estimate fully loaded agent hours
- 03Compare model-routing savings
- 04Estimate query energy and emissions
- 05Analyze proof-adjusted autonomy
- 06Return formulas and citation text
Use cases
- 01Plan LLM token budgets
- 02Estimate electricity use for AI queries
- 03Compare verification efficiency across agent tasks
- 04Assess human review team capacity
MCP support
It exposes 12 economics calculators to MCP clients, covering token costs, energy use, and agent verification.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @michalpiszczek/ai-economics-mcpAI_ECONOMICS_APIOverride the API base URL (defaults to https://piszczek.pl/tools/api). No API key is required.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
12Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| gw | string | No | API gateway enforcement (default 'intro') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off' |
| ttl | number | No | access-token TTL in seconds (default 3600) |
| edge | string | No | edge/CDN enforcement (default 'jwt') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off' |
| mesh | string | No | service-mesh enforcement (default 'jwt') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off' |
| rate | number | No | requests/min of one credential (default 60) |
| batch | string | No | batch/worker enforcement (default 'off') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off' |
Details
From the project READMEai-economics-mcp
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):
{
"mcpServers": {
"ai-economics": {
"command": "npx",
"args": ["-y", "@michalpiszczek/ai-economics-mcp"]
}
}
}
Claude Code one-liner:
claude mcp add ai-economics -- npx -y @michalpiszczek/ai-economics-mcp
Tools
| Tool | Answers |
|---|---|
token_cost | What do 1M tokens cost per month across GPT, Claude, Gemini, DeepSeek? |
context_window | How many tokens is 50 pages, does it fit, what does carrying it cost? |
agent_hour | What does one hour of an AI agent cost, fully loaded with verification? |
model_routing | How much does routing to a cheaper tier save per year? |
llm_energy | How much electricity does an AI query use? |
joules_per_verified_task | Which model is most efficient per task that actually passes? |
token_burn | What does org-wide token burn cost in money, kWh, CO₂? |
humanoid_energy | How long can a humanoid robot run per charge? |
proof_adjusted_autonomy | How autonomous is a "90% autonomous" agent once proof is required? |
revocation_exposure | How long does a revoked token keep working across your stack? |
verification_bottleneck | How many AI agents can a human review team absorb? |
proof_debt | What 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 var | Default | Purpose |
|---|---|---|
AI_ECONOMICS_API | https://piszczek.pl/tools/api | Point 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:
docker build -t ai-economics-mcp .
docker run -i --rm ai-economics-mcp
Concepts behind the tools
- Joule Wars — the AI race for energy efficiency
- Proof-Adjusted Autonomy — the metric of proven agent work
- Revocation Exposure — how long revoked authority keeps working
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).
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.