# io.github.vpatser1/ai-cost-analyzer (npm · ai-cost-analyzer)

Analyze LLM API costs: token waste detection, caching savings estimates, model comparison

- Trust score: 59/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- npm · `ai-cost-analyzer`: 59/100 (this document), [markdown](https://verifymcp.io/servers/vpatser1-ai-cost-analyzer/ai-cost-analyzer.md), [page](https://verifymcp.io/servers/vpatser1-ai-cost-analyzer/ai-cost-analyzer)

## Channel facts

- Registry: `npm`
- Package: `ai-cost-analyzer`
- Version: `1.1.4`
- 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 2026-08-07.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Known CVEs were checked across the 95 of 99 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 95 of 99 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 375 tokens (~75/item across 5 items; 5 tools + 0 resources), lean.
  - 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 vpatser1-ai-cost-analyzer -- npx -y ai-cost-analyzer
```

### Codex

```bash
codex mcp add vpatser1-ai-cost-analyzer -- npx -y ai-cost-analyzer
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vpatser1-ai-cost-analyzer": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "ai-cost-analyzer"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add vpatser1-ai-cost-analyzer --command npx --arg -y --arg ai-cost-analyzer
```

### Hermes

```yaml
mcp_servers:
  vpatser1-ai-cost-analyzer:
    command: "npx"
    args: ["-y", "ai-cost-analyzer"]
```

### Other

```json
{
  "mcpServers": {
    "vpatser1-ai-cost-analyzer": {
      "command": "npx",
      "args": [
        "-y",
        "ai-cost-analyzer"
      ]
    }
  }
}
```

## 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.

### 2026-08-04 (score 59)

First indexed and scored.

## MCP tools (5)

### `analyze_usage` (~56 tokens)

Analyze AI API usage data and return cost breakdowns by model, average cost per request, token waste estimation, and daily/weekly trends.

Input parameters:

- `usage_data` (array, required): Array of API usage records with model, tokens, and timestamps

### `estimate_savings` (~76 tokens)

Estimate potential monthly savings from prompt caching, model routing, and context pruning based on current usage patterns.

Input parameters:

- `monthly_multiplier` (number): If the usage_data is a sample, multiply costs by this factor to project monthly totals (default: 1)
- `usage_data` (array, required): Array of API usage records representing current usage patterns

### `optimize_prompt` (~111 tokens)

Analyze a system prompt and tool definitions, return an optimized version with redundant content removed, token counts before/after, and cost reduction estimates.

Input parameters:

- `model` (string): Model name for pricing calculation (default: claude-sonnet)
- `requests_per_month` (integer): Estimated requests per month for cost projection (default: 10,000)
- `system_prompt` (string, required): The system prompt text to optimize
- `tool_definitions` (array, required): Array of tool definition strings (JSON or plain text)

### `compare_models` (~93 tokens)

Compare cost and quality tradeoffs across Claude, GPT-4o, GPT-4o-mini, and Gemini models for a given task. Returns cost per request, monthly projections, and recommendations.

Input parameters:

- `estimated_input_tokens` (integer): Override estimated input tokens per request
- `estimated_output_tokens` (integer): Override estimated output tokens per request
- `task_description` (string, required): Description of the task to compare models for

### `get_pricing` (~39 tokens)

Return current pricing for all major LLM APIs (Claude, OpenAI, Gemini) with input, output, and cached token rates per million tokens.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/vpatser1-ai-cost-analyzer/ai-cost-analyzer#diagnostics

## Score history

- 2026-08-07: 59
- 2026-08-06: 59
- 2026-08-05: 59
- 2026-08-04: 59

## Links

- npm package: https://www.npmjs.com/package/ai-cost-analyzer
- Socket report: https://socket.dev/npm/package/ai-cost-analyzer
- Website: https://aivp-mcp.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/vpatser1-ai-cost-analyzer/ai-cost-analyzer.xml
- Changelog JSON feed: https://verifymcp.io/servers/vpatser1-ai-cost-analyzer/ai-cost-analyzer.json
- HTML version of this page: https://verifymcp.io/servers/vpatser1-ai-cost-analyzer/ai-cost-analyzer