Add the connector
In Claude open Settings, Connectors and choose Add custom connector. Name it What's Wrong and paste the server URL https://app.stillneedsahuman.com/mcp. Leave the client fields empty: Claude registers itself.
Connect What's Wrong to Claude or ChatGPT and ask for a check in the chat. The assistant runs the same check as the app with your workspace's profiles and gives you the report link. A person still signs the report off in the app.
https://app.stillneedsahuman.com/mcp
Runs checks, reads reports and findings, hands you the report as HTML, Excel, CSV or JSON and, where your workspace has it on, makes a corrected copy of a file and marks findings when you say so. It never signs a report off.
In Claude open Settings, Connectors and choose Add custom connector. Name it What's Wrong and paste the server URL https://app.stillneedsahuman.com/mcp. Leave the client fields empty: Claude registers itself.
Press Connect. A What's Wrong page opens: sign in, pick the workspace if you belong to several, keep the permissions you want and press Allow.
Turn the connector on from the tools menu of a chat and ask for a check. On a Team or Enterprise plan an owner adds the connector once; each person then connects and signs in as themselves.
The same URL works as a remote server in Claude Desktop and Claude Code. In a terminal the assistant can send a file to the upload link with curl.
In ChatGPT open Settings, Apps and Connectors, Advanced settings and turn on Developer mode. On a business plan a workspace admin may have to allow it first.
Choose Create. Name it What's Wrong, paste https://app.stillneedsahuman.com/mcp and pick OAuth. ChatGPT registers itself, so no client id is needed.
Sign in on the What's Wrong page and press Allow. In a chat pick the connector from the tools menu and ask for a check.
Every plan, Free and the trials included. A check from an assistant counts against the same monthly allowance of AI-reviewed words as a check in the app. The plan's limits apply the same way. While the connection is in early access we switch it on for each workspace: ask us and we turn it on for yours. Files, corrected copies and marking findings are switched on per workspace too.
You sign in to What's Wrong itself, never to the assistant. The assistant acts with your role in your workspace: a translator sees their own reports only, as in the app.
| Permission | What it allows | On the consent page |
|---|---|---|
| Read | Read your reports and profiles | ticked |
| Run | Run checks, which count against the workspace's AI allowance | ticked |
| Review | Mark findings Ignored or Fixed on your behalf, never sign a report off | not ticked |
Access lasts an hour at a time and renews while you stay connected. Disconnect an assistant at any time in Settings, Developer, Connected assistants.
Type one line at a time. The assistant picks the tools; you read the answer and open the report link.
“Check this file with the German support profile.” A small XLIFF goes in the chat; a bigger file goes through a one-time upload link.
“Give me the report as HTML.” The links open the same files the app makes, HTML, Excel, CSV or JSON.
“Which findings did the second opinion confirm, by segment?”
“Apply the confirmed fixes, recheck the copy and show me what changed.” Your original file is never changed.
“Ignore the quote style finding, reason: house style.” The app shows the mark as made through the assistant, with your reason.
“I have a 2 MB package.” The assistant gives you an upload link; drop the file there, say done and ask it to check the file.
Checks can also be run from an AI assistant; a file sent that way is handled as any other upload and removed within 24 hours. A corrected copy and the report download links work for one hour.
The assistant receives what the tools answer: results, findings with the segment text they are about and links. The text you check goes through the same rules and AI review as in the app, on the AI providers your workspace allows. Reports stay in your workspace until an admin deletes them. Read the privacy policy and the security page for the rest.
Something does not work or you want it on for your workspace? Tell us the time, the assistant and what you asked. Never send a token or a link from Settings.