claude-cost-mcp
firstshout/claude-cost-mcp
MCP server: Claude API token & cost estimation, prompt-caching break-even, Batch API savings, Claude-vs-GPT-vs-Gemini comparison. Local, no API key, Korean/CJK-aware.
Instalação
npx convez-ai firstshout/claude-cost-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
README
A tradução para o português deste README ainda está na fila.
claude-cost-mcp
MCP server that estimates Claude API token counts, per-model cost, and prompt-caching break-even — right inside Claude Desktop, Claude Code, Cursor, or any MCP client. Korean/CJK token-aware. Fully local, no API key, no network.
Built by claudeguide.io.
Tools
| Tool | What it does |
|---|---|
estimate_tokens | Token count for any text (Korean/CJK-aware — Korean costs ~30% more than English) |
estimate_cost | Cost across Haiku 4.5 / Sonnet 4.5 / Opus 4.5, with optional prompt-caching ratio and call count |
caching_breakeven | Prompt-caching savings + the ~1.28-reuse break-even point |
batch_savings | Batch API savings (50% off both directions) for async workloads — daily and monthly $ |
compare_providers | Cost table across 8 models / 3 providers (Claude vs GPT vs Gemini), sorted cheapest-first |
Pricing mirrors the 2026-05 canonical rates: Haiku $1/$5, Sonnet $3/$15, Opus $5/$25 per 1M tokens. Provider comparison uses verified 2026-05 public rates (OpenAI GPT-4o/-mini/o1, Google Gemini Flash/Pro 2.0).
Install
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"claude-cost": {
"command": "npx",
"args": ["-y", "claude-cost-mcp"]
}
}
}
Claude Code
claude mcp add claude-cost -- npx -y claude-cost-mcp
Then ask: "How much would a 2,000-token prompt with 800 tokens out cost on each Claude model?" or "How many tokens is this Korean paragraph?"
Run locally
npm install
npm test # 10 tests: pricing logic + live MCP handshake
npm start # stdio server
Why
Most developers guess at Claude costs and overpay — especially in Korean, where the same prompt uses ~1.3x the tokens. This puts accurate numbers one question away inside the tool you already use. Full benchmark and free calculators at claudeguide.io.
License
MIT