# pl.piszczek/ai-economics (npm · @michalpiszczek/ai-economics-mcp)

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

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@michalpiszczek/ai-economics-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/pl-piszczek-ai-economics/michalpiszczek-ai-economics-mcp.md), [page](https://verifymcp.io/servers/pl-piszczek-ai-economics/michalpiszczek-ai-economics-mcp)

## Channel facts

- Registry: `npm`
- Package: `@michalpiszczek/ai-economics-mcp`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 97/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1994 tokens (~166/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

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

### Codex

```bash
codex mcp add pl-piszczek-ai-economics -- npx -y @michalpiszczek/ai-economics-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pl-piszczek-ai-economics": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@michalpiszczek/ai-economics-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pl-piszczek-ai-economics --command npx --arg -y --arg @michalpiszczek/ai-economics-mcp
```

### Hermes

```yaml
mcp_servers:
  pl-piszczek-ai-economics:
    command: "npx"
    args: ["-y", "@michalpiszczek/ai-economics-mcp"]
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 65)

First indexed and scored.

## MCP tools (12)

### `revocation_exposure` (~260 tokens)

Revocation Exposure: How long does a revoked token keep working across gateways, caches and workers? Returns the worst-case exposure window, an A–F grade and the weakest enforcement point. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/revocation-exposure. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `batch` (string): batch/worker enforcement (default 'off') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off'
- `edge` (string): edge/CDN enforcement (default 'jwt') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off'
- `gw` (string): API gateway enforcement (default 'intro') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off'
- `mesh` (string): service-mesh enforcement (default 'jwt') — 'jwt' | 'intro' | 'poll:N' (seconds) | 'off'
- `rate` (number): requests/min of one credential (default 60)
- `ttl` (number): access-token TTL in seconds (default 3600)

### `proof_adjusted_autonomy` (~177 tokens)

Proof-Adjusted Autonomy (PAA): How autonomous is an AI agent once proof is required? PAA = P(A) × P(C|A) × P(R|A,C) × P(T|A,C,R). Returns the honest percentage, the gap vs claimed autonomy and the single gate where +5pp pays most. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/proof-adjusted-autonomy. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `a` (number): autonomous completion % (default 90)
- `c` (number): complete evidence % (default 95)
- `r` (number): independent validation % (default 80)
- `t` (number): timeliness % (default 90)

### `token_cost` (~129 tokens)

AI Token Cost: What does a monthly token volume cost across GPT, Claude, Gemini and DeepSeek? Input/output priced separately, prompt-cache discount applied. Returns the ranked bill per model. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/token-cost. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `cache` (number): prompt-cache hit % (default 40)
- `in` (number): input Mtok/month (default 200)
- `out` (number): output Mtok/month (default 20)

### `context_window` (~134 tokens)

Context Window: How many tokens is this content, does it fit the window, and what does carrying it cost per request? All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/context-window. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `amount` (number): quantity (default 50)
- `price` (number): $ per 1M input tokens (default 3)
- `unit` (string): words | pages | chars | loc (default pages)
- `window` (number): context size in tokens (default 128000)

### `agent_hour` (~146 tokens)

Agent-Hour Cost: Fully-loaded cost of one AI agent-hour: compute plus human verification, vs the human hour it replaces. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/agent-hour. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `human_rate` (number): human $/h it replaces (default 60)
- `price` (number): blended $/1M tokens (default 6)
- `review_min` (number): human verification minutes per agent-hour (default 15)
- `tokens_m` (number): Mtok consumed per agent-hour (default 1.5)

### `model_routing` (~122 tokens)

Model Routing Savings: How much does routing the routable share of a workload to a cheaper tier save per month and per year? All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/model-routing. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `ratio` (number): cheap tier price as % of flagship (default 20)
- `share` (number): routable share % (default 60)
- `spend` (number): monthly flagship spend $ (default 15849)

### `llm_energy` (~165 tokens)

LLM Energy: How much electricity does an AI query use? Tokens → Wh, joules, dollars, CO₂ and real-world equivalents. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/llm-energy. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `gco2_kwh` (number): gCO₂ per kWh (default 400)
- `j_per_token` (number): joules per token (default 1)
- `queries` (number): queries per day (default 1000)
- `tokens` (number): tokens per query (default 1000)
- `usd_kwh` (number): $ per kWh (default 0.15)

### `joules_per_verified_task` (~194 tokens)

Joules per Verified Task: Which model is most energy-efficient per task that actually passes verification? E = tokens × J/token ÷ pass rate — a lighter model with a lower pass rate can still win. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/joules-per-verified-task. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `ja` (number): model A J/token (default 1)
- `jb` (number): model B J/token (default 0.3)
- `pa` (number): model A verified pass % (default 80)
- `pb` (number): model B verified pass % (default 55)
- `ta` (number): model A tokens/attempt (default 8000)
- `tb` (number): model B tokens/attempt (default 15000)

### `token_burn` (~147 tokens)

Token Burn Meter: Org-wide token burn as money, kilowatt-hours, CO₂ and households powered — per day and per year. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/token-burn. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `gco2_kwh` (number): gCO₂ per kWh (default 400)
- `j_per_token` (number): joules per token (default 1)
- `price` (number): blended $/1M tokens (default 4)
- `tokens_day` (number): tokens per day (default 316000000)

### `humanoid_energy` (~156 tokens)

Humanoid Energy Budget: How long can a humanoid robot run per charge? Splits the battery between actuation, inference and idle. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/humanoid-energy. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `actuation_w` (number): W while moving (default 400)
- `battery_kwh` (number): battery capacity kWh (default 2)
- `compute_w` (number): inference W, always on (default 150)
- `duty` (number): active duty cycle % (default 60)
- `idle_w` (number): overhead W (default 40)

### `verification_bottleneck` (~175 tokens)

Verification Bottleneck: Agents generate in parallel, humans review in series. Computes the real agent-fleet ceiling from review capacity, minutes per task and rework rate. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/verification-bottleneck. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `agents` (number): planned agents (default 10)
- `hours` (number): review h/person/week (default 6)
- `min_per_task` (number): review minutes per task (default 10)
- `reviewers` (number): people reviewing (default 4)
- `rework` (number): rework % (default 20)
- `tasks_per_agent` (number): tasks per agent per week (default 60)

### `proof_debt` (~189 tokens)

Proof Debt Accumulator: What does unverified AI work cost over time? Backlog, deferred-review premium and expected incident liability. All parameters optional — defaults mirror the interactive calculator at https://piszczek.pl/tools/proof-debt. The response includes result, formula, interpretation and a ready-to-quote cite_as sentence.

Input parameters:

- `incident_cost` (number): $ per incident (default 25000)
- `incident_pct` (number): incident %/unverified task (default 0.5)
- `late_mult` (number): late-review multiplier (default 3)
- `tasks_week` (number): tasks per week (default 224)
- `unverified` (number): % shipped unverified (default 35)
- `verify_cost` (number): $/task to verify now (default 15)
- `weeks` (number): horizon in weeks (default 26)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pl-piszczek-ai-economics/michalpiszczek-ai-economics-mcp#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 65

## Links

- npm package: https://www.npmjs.com/package/@michalpiszczek/ai-economics-mcp
- Socket report: https://socket.dev/npm/package/@michalpiszczek/ai-economics-mcp
- Repository: https://github.com/pich/ai-economics-mcp
- Website: https://piszczek.pl/tools
- Changelog RSS feed: https://verifymcp.io/servers/pl-piszczek-ai-economics/michalpiszczek-ai-economics-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/pl-piszczek-ai-economics/michalpiszczek-ai-economics-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/pl-piszczek-ai-economics/michalpiszczek-ai-economics-mcp