Etuki FinOps & LLM Pricing Oracle

Connect Remote server

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

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

{
  "servers": {
    "etuki-finops-mcp": {
      "type": "http",
      "url": "https://www.etuki.com/api/v1/mcp"
    }
  }
}

Settings > Connectors > Add custom connector
URL: https://www.etuki.com/api/v1/mcp

Tools 9 found in our last check

• 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 no API keys; unknown model IDs safely fall back to the flagship baseline without error. Sums burned_usd and remaining_us…

• 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. Stateless in-memory calculation requiring no authentication and mutating no router settings. Scales per-turn cost linearl…

• 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 registry. Deterministic local snapshot lookup that issues zero network probes, requires no API keys, and consumes zero…

• 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 traces, and file paths. Deterministic in-memory string transformation that mutates no files and requires no authenticatio…

• 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 provider cache-control templates. In-memory actuarial lookup requiring no API keys; unknown model IDs default to 'openai/gpt-…

• 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 unutilized prefix cache waste. Deterministic mathematical audit in memory requiring no authentication. Returns JSON with expec…

• 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. Advisory in-memory simulation that mutates no live prompts and requires no authentication; zero-token inputs return 0 USD cos…

• 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 272K on GPT-6.1 Sol) and returns the surcharge multiplier and recommended flat-context alternative. Deterministic thresho…

• 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, and Merkle leaf hashes. Deterministic local lookup requiring no API keys; unknown vendor slugs safely return total_matc…

Details

More ai and media servers See all

• bv7x strategy agents

  Find bv7x prediction agents on Robinhood Chain by market; quote their sealed calls, sold via x402.

• Chronary

  Calendar API for AI agents: events, availability, Google/Microsoft setup, scheduling, and iCal.

• Mastering

  Audio mastering for AI agents: LUFS analysis, Suno artifact cleanup, free daily master.

• Modulos AI Governance Platform

  Evaluate Modulos (EU AI Act, ISO 42001, NIST AI RMF): capabilities, trust, comparisons. Book a demo.

• naulon

  Check citations and retractions by DOI, and see the x402 price an AI agent pays to cite a source.

• NextConstraint

  Your SaaS funnel's costliest leak, its fix, watchdog alerts and verdicts, from NextConstraint.