/reright

Connect from the cloud

Claude.ai, Claude Desktop, ChatGPT and Claude Projects run on the provider's servers, not on your machine. You add reright to them as a connector. The assistant then sends the text it writes for you to reright and uses the text that comes back, so it sounds like you wrote it. The hook that the Claude Code installer sets up cannot reach these clients. This page shows how to connect them, and says plainly what a connector does and does not do.

What a connector can and cannot do

A connector gives the assistant three tools: rewrite, rewrite_result and keep_original. With the instructions below, the assistant sends its text to rewrite and uses the text that comes back.

It does not block anything. A chat client has no hook that can stop a message, a commit or an email. If the assistant ignores the instructions, or you tell it to skip reright, the text goes out as the assistant wrote it and reright never sees it. Blocking only works where a hook can run, which means Claude Code on your own machine, set up by the installer.

The server URL

Every client asks for the same address, which is also in Settings under Connect. Sign-in is OAuth with your reright account, so there is no token to copy.

https://app.reright.it/mcp

If the client asks how it should identify itself to the server, choose to register automatically (dynamic client registration).

Claude.ai and Claude Desktop

The steps are the same in the browser and in the desktop app.

  1. Open Customize, then Connectors.
  2. Select Add custom connector.
  3. Paste the server URL above and select Add.
  4. Select Connect and sign in to reright when the page opens.
  5. In a chat, open the + menu, choose Connectors and switch reright on for that conversation.

A Free plan can add one custom connector. On Team and Enterprise plans an Owner adds it once under Organization settings, Connectors, Add, Custom, Web, and each member then selects Connect with their own account. Menu names can change, so Anthropic's guide is the reference.

Claude can ask before each tool call. Leave that on for the first few rewrites, and only choose "Always allow" once you trust how it behaves.

ChatGPT

ChatGPT adds remote servers in developer mode, which is limited to some plans and can be turned off by a workspace admin.

  1. Turn on developer mode in ChatGPT settings, under Connectors.
  2. Create a new connector, give it a name such as reright, and paste the server URL above.
  3. Choose OAuth, create it, and sign in to reright.
  4. In a new chat, switch the connector on for that chat.

OpenAI's developer mode guide has the current steps.

Claude Code only

If you use Claude Code, paste the setup line from Settings instead, which runs the installer. It adds the same server and the hook that blocks text that did not come back from reright. To add only the tools, without the hook:

claude mcp add --transport http reright https://app.reright.it/mcp

Projects and custom instructions

A connector only makes the tools available. The assistant has to be told to use them. Add this to the instructions of a Claude Project, to ChatGPT's custom instructions or project instructions, or to the system prompt of any other assistant:

Use reright only for text someone besides me will read: emails, messages to other people, posts, comments, PR and commit text in shared repos, and drafts I will send. Skip it for replies to me, my own notes and docs, code and config. If you can't tell, ask me once. For that text, call rewrite on the reright server with the exact text, its kind, where it goes and a line of context. Send only the words a person writes, not links, names, versions or code. If the status is pending, give me the review link once and call rewrite_result with the id until it is not. If it is rejected, stop, do not retry or rephrase, and wait for my instructions. When it is approved, use final_text exactly, character for character: I want the rewrite, and your own text sounds like AI. Call keep_original only if the rewrite changed a fact, name, number, date, yes or no or promise, and quote the phrase from each version. Wording, tone or style is not a reason.

This is a short version for chat clients. The full rules text, which the installer writes for Claude Code, is in the docs.

Check that it works

  1. In a new chat with the connector on, write: "Use reright on this message before you show it to me: Hello, the report is ready."
  2. The assistant should call rewrite and show you the text that came back.
  3. If "Check before it's used" is on, it gives you a review link first. Open it, edit the text if you like, and approve. The assistant should then show you the approved text, unchanged.

If you registered using an email address, confirm it from the link we send before. Otherwise the assistant gets an error that takes you to Settings.

If reright has been idle for a while, the first rewrite can take longer than a minute. The assistant then gets its own text back, and the next rewrite is faster.

If nothing comes back, check that the connector is switched on for that chat and that you connected it. If the assistant shows text without calling reright, that is the limit described at the top: it has no hook, so nothing stopped it.