convez.ai
MCP Server
firstshout

claude-cost-mcp

firstshout/claude-cost-mcp

Ver no GitHub
InicialPluginScore · de 0 a 100

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-mcp

1 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

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

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

ToolWhat it does
estimate_tokensToken count for any text (Korean/CJK-aware — Korean costs ~30% more than English)
estimate_costCost across Haiku 4.5 / Sonnet 4.5 / Opus 4.5, with optional prompt-caching ratio and call count
caching_breakevenPrompt-caching savings + the ~1.28-reuse break-even point
batch_savingsBatch API savings (50% off both directions) for async workloads — daily and monthly $
compare_providersCost 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

Ver o original no GitHub

Bom para

Relacionados