Checks if a cheaper model agrees with your GPT, Claude or Gemini outputs, and what routing saves.
Connect Remote server
claude mcp add --transport http audit https://api.llmcutover.com/mcp --header "Authorization: Bearer <YOUR_API_KEY>"
{
"mcpServers": {
"audit": {
"url": "https://api.llmcutover.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}
{
"servers": {
"audit": {
"type": "http",
"url": "https://api.llmcutover.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}
Settings > Connectors > Add custom connector
URL: https://api.llmcutover.com/mcp
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools 2 found in our last check
run_cutover_auditMeasures 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 hybrid. Returns the full report as JSON.
list_modelsCurrent models with $/1M token prices and effort levels, usable as current.model.
Headers
| Name | Description |
|---|---|
AuthorizationOptional, secret | Optional. 'Bearer <full-audit pass>' for paid runs; without it you get the free tier (3 audits/day, 10 samples). |
Details
| Endpoint | https://api.llmcutover.com/mcp (Streamable HTTP) |
| First published | 3 Nov 2026 |
| Last updated | 3 Nov 2026 |
| Registry name | com.llmcutover/audit |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
