com.llmcutover/audit

up checked 2026-11-11T09:39:54.647Z

Unclaimed · Unverified

Publisher-provided title

LLM Cutover

Publisher-provided description

Checks if a cheaper model agrees with your GPT, Claude or Gemini outputs, and what routing saves.

Summary by lookupd

Measures how often a cheaper model agrees with your current LLM outputs and estimates monthly cost savings from routing.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http audit https://api.llmcutover.com/mcp

Codex, remote (streamable-http)

codex mcp add audit --url https://api.llmcutover.com/mcp

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

{
  "mcpServers": {
    "audit": {
      "url": "https://api.llmcutover.com/mcp"
    }
  }
}

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

Publisher-provided text

run_cutover_audit Measures how often a cheaper model (Sage 2) agrees with your current LLM on your samples, the confidence threshold for routing, and the monthly cost now vs a hy
list_models Current models with $/1M token prices and effort levels, usable as current.model.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.llmcutover/audit.svg)](https://lookupd.com/servers/com.llmcutover/audit)