Etuki FinOps & LLM Pricing Oracle

io.github.cooyunPublished by GitHub account cooyunv40.7.4Updated Nov 1, 2026

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

VerifiedStreamable HTTPWeb executableFinanceData & AnalyticsAI & ML

Overview

AI-generated overview

Remote Etuki MCP server that checks an LLM request's token counts against a pricing snapshot and returns allow, warning, reroute or block decisions with cost…

What you can do
  • Check a single LLM request's token counts against a pricing snapshot and get a deterministic allow, pre-cliff warning, hard-cliff reroute or budget-gate block, with estimated costs and a cheaper fallback model.
  • List the five cliff-engine models with their input/output and cache rates, cliff and soft-block thresholds, fallback targets and snapshot identifiers.
  • Search and filter the catalog of 563 LLM API and cloud infrastructure entities by keyword.
  • Retrieve audit evidence for the current pricing snapshot, such as the Merkle root, public key location, snapshot date and CI self-test reference.
When to use it
Useful when you want an assistant to sanity-check token volume and estimated cost before sending a large or long-context LLM request, or to look up model rates and cheaper fallbacks. Also suited to teams that want a documented, auditable pricing snapshot reference.
Requirements
A remote MCP endpoint at etuki.com over streamable HTTP; no package install, environment variables or headers are declared. The README's quickstart uses a downloaded script run with Node.js, which is separate from the MCP endpoint.
Before you install
Cost figures are estimates, not billing. The server returns pricing and routing decisions that could influence spending, so verify against your provider's actual invoices. The README also advertises a paid Pro trial and browser tools on the vendor site; treat those as third-party offerings.

Installation

In SourceWeft

  1. Open Etuki FinOps & LLM Pricing Oracle in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.cooyun%2Fetuki-finops-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

README

🛡️ etuki-gate — AI FinOps Context-Cliff & Token Budget CI Gate

[Merkle Verified Pricing] [Zero Dependencies] [License: MIT]

Stop losing 50%–80% of your monthly LLM API budget to hidden long-context pricing cliffs (>272K 2x surcharge on OpenAI Sol/Pro, >100K 5x surcharge on Claude Haiku) and unpinned prefix caches. Powered by Etuki Intelligence (etuki.com) — the 3D AI FinOps Control Plane, Local CSV Bill X-Ray & Context Quota Studio.

⚡ 10-Second Quickstart (Zero Install)

bash
curl -sSfL https://www.etuki.com/etuki-gate.mjs -o etuki-gate.mjsnode etuki-gate.mjs --testnode etuki-gate.mjs --model gpt-6-1-sol --in 285000 --out 20000

🌐 Interactive Web Tools (100% Browser-Local Privacy)

Source: README.md at commit cc2a8f0

Tools

4

check_context_cliff

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.

Parametersmodelrequiredpass_raterequest_idretry_rateprompt_tokensrequiredcache_hit_ratebudget_gate_usdallow_async_batchcompletion_tokensrequiredrouted_cache_hit_ratecold_start_cache_write

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.

Takes no parameters.

etuki_search_models

Search and filter across all 563 Merkle-committed LLM API and cloud infrastructure entities in the Etuki catalog by keyword.

Parametersquery

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.

Takes no parameters.

Version history

1
  1. v40.7.4LatestNov 1, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.