Skip to main content
Glama
Sign In
claude-cost-mcp

claude-cost-mcp

by firstshout
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

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).

Related MCP server: contextburn

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

Available Tools

5 tools
batch_savingsA

Compute Batch API savings (50% off input+output) for a recurring workload. Use when work is async/non-realtime (≤24h SLA acceptable).

Inputs: input_tokens (required), output_tokens (required), calls_per_day (required), model.

caching_breakevenA

Compute prompt-caching savings and break-even for a static prompt reused N times. Break-even is ~1.28 reuses.

Inputs: prompt_tokens (required), reuses (required), model.

compare_providersA

Compare API cost across 8 models from Anthropic, OpenAI, and Google for given token counts. Returns a table sorted cheapest-first so you can see where Claude sits vs alternatives.

Inputs: input_tokens (required), output_tokens (required), calls_per_month.

estimate_costA

Estimate Claude API cost across Haiku/Sonnet/Opus for given token counts (or raw text). Optional prompt-caching ratio.

Inputs: input_text, input_tokens, output_tokens, cache_ratio, +1 more.

estimate_tokensA

Estimate the number of Claude tokens for a piece of text. Korean/CJK-aware (Korean uses ~1.3x the tokens of equivalent English). No API key needed.

Inputs: text (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A4.1/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clear, distinct purpose: batch savings, caching break-even, provider comparison, cost estimation, and token estimation. No overlap between them.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern (e.g., batch_savings, estimate_cost), making them predictable.

    Tool Count5/5

    Five tools is an appropriate size for a cost-estimation server, each covering a necessary aspect without being excessive or insufficient.

    Completeness4/5

    The tool set covers core cost estimation, token counting, batch savings, caching efficiency, and provider comparison. Minor gaps like historical usage tracking exist but are not essential for the stated purpose.

    Resources

    Related MCP Connectors

    Related MCP Servers