78trust / 100

Etuki FinOps & LLM Pricing Oracle

by etuki.com in Onchain & crypto

MCP serverPassing, checked 10 h ago

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

https://www.etuki.com/api/v1/mcp
Tools
7
open to any client
Uptime
91.7%
last 30 days
Response time
413 ms
601 ms slowest 5%
Last check
Passed
10 h ago, next any minute now

Scan it nowHow to connect

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to connect

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "etuki-finops-llm-pricing-oracle": {
      "type": "http",
      "url": "https://www.etuki.com/api/v1/mcp"
    }
  }
}

7 tools

  • compress_and_fold_context

    SINGLE-MODEL CONTEXT & TOOL-OUTPUT COMPRESSOR: Folds verbose logs, duplicate lines, and oversized tool outputs by 65%-92% in-memory so you save money on your CURRENT single model (works with GLM-5v-Turbo, Claude 3.7 Sonnet, GPT-4.1, Gemini 2.5 Pro, DeepSeek-R1, Qwen-Max) without…

  • pin_single_model_prefix_cache

    SINGLE-MODEL PREFIX CACHE REARRANGER: Saves 75%-90% on your CURRENT single model without switching models! Automatically strips volatile timestamps/UUIDs from your system prefix, moves them to the suffix, folds old middle turns, and aligns 4 cache breakpoints.

  • chunk_below_context_cliff

    SINGLE-MODEL CLIFF SPLITTER: Splits >128K / >200K token documents into sub-cliff windows for your existing single model so you never pay 2x context-cliff surcharges or suffer 120s gateway timeouts.

  • check_context_cliff

    Calculates exact token cost on ANY model (natively supports GLM-5v-Turbo, GPT-4.1, Claude 3.7 Sonnet, Gemini 2.5 Pro, DeepSeek-R1, Qwen-Max + 563 entities) and returns a Single-Model In-Place Saving Plan FIRST (no model switching required!). Receives model name and token counts…

  • list_supported_models

    Returns verified Production GA models (including Zhipu GLM-5v-Turbo, OpenAI GPT-4.1/4o, Claude 3.7 Sonnet, Gemini 2.5 Pro/Flash, DeepSeek-R1/V3, Qwen-Max, Kimi-k2) with exact rate cards, cache discounts, and cliff thresholds.

  • etuki_search_models

    Searches all 563 indexed LLM models & cloud infrastructure services by keyword (e.g. glm, qwen, deepseek, claude, gpt-4.1, gemini).

  • etuki_get_audit_evidence

    Returns cryptographic Merkle root, RS256 signature envelope, and pricing snapshot verification metadata.

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
10 h agoPassed200289 ms
21 h agoPassed200264 ms
32 h agoPassed200413 ms
45 h agoPassed200314 ms
3 days agoPassed200461 ms
Show 7 older checks
3 days agoPassed200451 ms
4 days agoPassed200280 ms
4 days agoPassed200469 ms
5 days agoPassed200601 ms
6 days agoPassed200222 ms
6 days agoinitialize returned HTTP 405405173 ms
6 days agoPassed200435 ms