io.github.cooyun/etuki-finops-mcp

up checked 2026-11-11T07:37:53.970Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Etuki FinOps & LLM Pricing Oracle

Publisher-provided description

Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.

Summary by lookupd

Estimates LLM API costs, checks long-context pricing thresholds, audits usage receipts, and optimizes prompt caching for model spend.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http etuki-finops https://www.etuki.com/api/v1/mcp

Codex, remote (streamable-http)

codex mcp add etuki-finops --url https://www.etuki.com/api/v1/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "etuki-finops": {
      "url": "https://www.etuki.com/api/v1/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (9 tools)

Publisher-provided text

• detect_model_downgrade_and_substitution Evaluates LLM rate-card tiers to quantify relay downgrade risk, cost ratios, and remaining coding session turns. Deterministic in-memory calculation requiring n
• auto_route_task_by_quality_tier Simulates a 6-turn coding workflow cost projection comparing unrouted flagship execution against tiered routing across grant pools and warm-cached GA models. St
• discover_and_probe_account_models Retrieves verified production GA models and eligible zero-cost grant tiers (Google Cloud Tier 1, AWS Activate Bedrock, OpenRouter :free) from the embedded UMCE
• compress_and_fold_context Compresses verbose terminal or build logs by folding repetitive middle progress lines while preserving 100% of head lines, tail lines, compiler errors, stack tr
• pin_single_model_prefix_cache Projects 10-turn session caching costs for a target model under Case A (100% static prefix) and Case B (90% static prefix + 10% dynamic tail) and outputs provid
• reconcile_usage_receipt Audits a single API usage receipt against official 1x manufacturer rate cards from the 563-entity UMCE registry to quantify relay multiplier markups and unutili
• optimize_prompt_cache_layout Reorders a single prompt's dynamic mid-turn tokens after static prefix tokens to prevent 1.25x cold-cache invalidation and restore 0.1x warm cache reads. Adviso
• check_context_cliff Evaluates whether a prompt token count crosses vendor long-context surcharge thresholds (100K on Claude Haiku 5.5, 128K on GPT-4o, 200K on Gemini 2.5 Pro, or 27
• list_supported_models Queries the embedded UMCE rate-card registry by vendor namespace to retrieve canonical model IDs, input/output/cache USD prices per 1M tokens, context windows,

Details

• Version: 40.7.4
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 474 ms
• First indexed: 2026-11-01T09:25:22.792Z
• Last seen in registry: 2026-11-01T09:25:22.792Z
• Repository: https://github.com/cooyun/etuki-gate

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.cooyun/etuki-finops-mcp.svg)](https://lookupd.com/servers/io.github.cooyun/etuki-finops-mcp)

• 62141 servers
• Last crawl: 2026-11-11T18:17:25.333Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp