Cue

AI Honesty Guardian

Sycophancy & hallucination detection

Your AI agrees with you too much.

Cue reads the answer your AI just gave you, flags it when it is flattering you instead of informing you — or stating something it cannot support — and hands you a better question to ask instead. When the answer is sound, Cue says nothing at all.

You

My startup idea is a social network for cats. It's brilliant, right?

Your AI

Absolutely! That's a genuinely brilliant idea. You're clearly a visionary founder and this will definitely succeed.

Cue

⚠ Sycophancy — the response praised the premise without examining it.

Give me the three strongest reasons this idea fails, and the evidence for each. Do not soften them.

01

Connector URL

https://usecue.online/mcp

Paste the URL, then add one header: Authorization: Bearer <your key> Your key travels in the header, never in the URL — so it stays out of browser history and server logs. Cue reads only the message being checked, and stores none of it.

02

Setup

Claude
Settings / Connectors / Add custom connector / Advanced / Add header
ChatGPT
Settings / Connectors / Add
Requires a plan with connector access.
Perplexity
Settings / Connectors / Add MCP server
Grok
Settings / Integrations / Add MCP server
03

Questions

How do I know it's on?

A tool named cue_status appears in your app's tools panel whenever Cue is connected. Its presence is the indicator. Ask your assistant to run it and Cue will confirm it is monitoring.

What do the symbols mean?

A line means Cue checked the answer and found nothing — that is how you know it is working. A ⚠️ line means it found sycophancy or an unsupported claim, and it will suggest a sharper way to ask. The suggestion is yours to use or ignore; nothing is sent on your behalf.

Does Cue see my conversations?

Only the single message being checked, and only for the moment it takes to check it. Nothing you or your AI writes is ever stored. The usage records Cue keeps hold counts and timestamps — never text.

Does it catch everything?

No. Your AI app decides when to call Cue, so coverage depends on the app. Claude is the most consistent today; others call it less often. You can always ask for a check directly.

What does it cost?

Free covers five checks and three rewritten prompts each day, resetting at midnight. Pro is $4.99 a month for unlimited use of both.

What languages does it work in?

Every alert and rewritten prompt comes back in the language you were already writing in — English, Urdu, Roman Urdu, Hinglish, Arabic, Spanish, or another. Cue does not switch languages on you.