Etuki FinOps & LLM Pricing Oracle
Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.
使うべきか
品質と安全性
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": {
"etuki-finops-mcp": {
"url": "https://www.etuki.com/api/v1/mcp"
}
}
}リモートエンドポイント
https://www.etuki.com/api/v1/mcpstreamable-httpできること
ツール一覧
ツール（4）
🟢check_context_cliff(model, prompt_tokens, completion_tokens, request_id, cold_start_cache_write, ...)
Check one LLM request's token counts against a pricing snapshot and return a deterministic decision: allow, pre-cliff warning, hard-cliff reroute, or budget-gate block, with estimated costs and a cheaper fallback model where one exists. Estimates only, not billing. Receives model name and token counts only, never prompt content.
入力スキーマ
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model ID from list_supported_models (gpt-6-1-sol, claude-haiku-5-5, claude-sonnet-5-5, claude-opus-5-5, gpt-6-luna)"
},
"prompt_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"completion_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"request_id": {
"type": "string",
"maxLength": 64,
"pattern": "^[a-zA-Z0-9_-]{1,64}$",
"description": "Optional trace ID (1..64 alphanumeric/underscore/hyphen chars)."
},
"cold_start_cache_write": {
"type": "boolean",
"default": false
},
"allow_async_batch": {
"type": "boolean",
"default": true
},
"budget_gate_usd": {
"type": "number",
"minimum": 0,
"default": 0.06
},
"cache_hit_rate": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.4
},
"routed_cache_hit_rate": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"retry_rate": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.05
},
"pass_rate": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 1,
"default": 0.96
}
},
"required": [
"model",
"prompt_tokens",
"completion_tokens"
],
"additionalProperties": false
}🟢list_supported_models
Return the 5 deterministic cliff-engine models supported by check_context_cliff along with their input/output rates, cache rates, cliff token thresholds, soft-block thresholds, fallback targets, pricing_snapshot_id, and Merkle root.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢etuki_search_models(query)
Search and filter across all 563 Merkle-committed LLM API and cloud infrastructure entities in the Etuki catalog by keyword.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Model or vendor keyword (e.g. gpt-6.1, claude, gemini, deepseek, hunyuan)"
}
},
"additionalProperties": false
}🟢etuki_get_audit_evidence
Retrieve the cryptographic snapshot metadata (Merkle root, RS256 public key URL, snapshot date, and 12/12 CI self-test reference) for the current pricing snapshot.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}コミュニティ
エビデンス