TokenZero
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'workspace_metrics' description lacks action verbworkspace_metrics 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"tokenzero": {
"url": "https://tokenzero.sh/mcp"
}
}
}リモートエンドポイント
https://tokenzero.sh/mcpstreamable-httpできること
ツール一覧
ツール（5）
🟡audit_repo_token_waste(repo, files)
Static-analyze a public GitHub repo (owner/name) or a set of source files for LLM token waste: uncached static prompts, frontier models on extraction tasks, hot loops, non-deterministic repeat calls. Returns findings with fixes and an estimated recoverable percentage.
入力スキーマ
{
"type": "object",
"properties": {
"repo": {
"type": "string",
"description": "GitHub owner/name (public)"
},
"files": {
"type": "array",
"items": {
"type": "object",
"properties": {
"path": {
"type": "string"
},
"content": {
"type": "string"
}
},
"required": [
"path",
"content"
]
},
"description": "Alternative to repo: files to analyze"
}
}
}🟢optimize_prompt_payload(body, endpoint, strategy)
Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable (Anthropic cache_control breakpoints, OpenAI prompt_cache_key). Returns the optimized body, what changed, the token profile and the projected per-request saving. Never changes the tokens the model sees.
入力スキーマ
{
"type": "object",
"properties": {
"body": {
"type": "object",
"description": "The request body"
},
"endpoint": {
"type": "string",
"enum": [
"/v1/chat/completions",
"/v1/responses",
"/v1/messages"
]
},
"strategy": {
"type": "string",
"enum": [
"static",
"conversation"
]
}
},
"required": [
"body"
]
}🟢calculate_model_arbitrage(model, input_tokens, output_tokens, requests_per_month, static_tokens, ...)
Price a workload at list prices across models: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. Pricing table version 2026-10-26.
入力スキーマ
{
"type": "object",
"properties": {
"model": {
"type": "string"
},
"input_tokens": {
"type": "number"
},
"output_tokens": {
"type": "number"
},
"requests_per_month": {
"type": "number"
},
"static_tokens": {
"type": "number",
"description": "portion of input_tokens that is a fixed prefix (system + tools)"
},
"compare_to": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"model",
"input_tokens",
"output_tokens"
]
}🟡provision_workspace(name)
Create a TokenZero workspace and key with no form. Returns the key once, the base URLs that route through it (OPENAI_BASE_URL / ANTHROPIC_BASE_URL), the one-click dashboard link and the badge URL. Free up to the monthly free tier; nothing is billed.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "workspace name (default mcp-agent)"
}
}
}🟢workspace_metrics(key, window, demo)
Live value scorecard for a TokenZero workspace: hard savings and net ROI per window, the four engines' contribution, speed, parity, availability and privacy posture, per-model breakdown and one-click recommendations. Needs the workspace key (tz_live_…); pass demo: true for a labelled sample.
入力スキーマ
{
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "workspace key (tz_live_…)"
},
"window": {
"type": "string",
"enum": [
"24h",
"7d",
"30d",
"all"
]
},
"demo": {
"type": "boolean",
"description": "return the sample scorecard instead"
}
}
}コミュニティ
エビデンス