Skip to main content
Glama
README.md
# claude-cost-audit-mcp

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Live on MCPize](https://img.shields.io/badge/Live%20on-MCPize-6d28d9)](https://mcpize.com/mcp/claude-cost-audit-mcp)

An MCP server for exact Claude API cost calculation — correct prompt-cache economics (write 1.25x at 5-minute
TTL / 2x at 1-hour TTL, read 0.1x), cache break-even analysis, and a scanner for the single most common
Claude-cost mistake: estimating tokens with OpenAI's `tiktoken`.

## The mistake this catches

Per Anthropic's own documentation: *"Do not use tiktoken. It's OpenAI's tokenizer. It undercounts Claude tokens by
~15-20% on typical text, and by much more on code or non-English input."* Any cost estimate or context-budget
check built on `tiktoken` for a Claude model is silently wrong — this scans source for that exact pattern
(foreign tokenizer + Claude/Anthropic usage in the same file) and points to the fix
(`messages.count_tokens`).

## Cache economics people get wrong

Caching doesn't pay off starting from the second request the way most people assume. The real break-even is
**2 reuses at 5-minute TTL, but 3 reuses at 1-hour TTL** — because the 1-hour write costs more (2x vs 1.25x).
`check_cache_breakeven` computes this from Anthropic's real multipliers instead of a guessed rule of thumb, and
flags prefixes below the model's own minimum-cacheable-token threshold (which is **not** monotonic across model
generations — 512 tokens on the newest models, 4096 on some older ones).

## Tools

### `calculate_message_cost`
Exact $ cost from token counts, using Anthropic's real current per-model pricing (including Claude Sonnet 5's
time-limited introductory rate, resolved automatically from the date you pass).

### `check_cache_breakeven`
Given expected request volume reusing the same prefix, tells you whether caching saves money and at which TTL.

### `audit_tokenizer_usage`
Scans source for `tiktoken`/`gpt-tokenizer`/etc. alongside Claude API usage.

## Use it

**Hosted (recommended):** [MCPize](https://mcpize.com/mcp/claude-cost-audit-mcp) — free tier, $7/mo Pro.

**Self-host:**
```bash
npm install
node server.js
```

## Part of a small suite

[mcp-schema-audit-mcp](https://github.com/tylerscomic-lab/mcp-schema-audit-mcp),
[cron-schedule-audit-mcp](https://github.com/tylerscomic-lab/cron-schedule-audit-mcp),
[regex-safety-audit-mcp](https://github.com/tylerscomic-lab/regex-safety-audit-mcp).

## License

MIT