# ChatGPT

Source: /docs/mcp/connect/chatgpt

ChatGPT connects to OrbitOrca over **OAuth** — you add OrbitOrca's server URL, approve OrbitOrca on a consent screen, and ChatGPT holds the connection. There's no config file and no token to paste.

> Adding a custom MCP server needs ChatGPT's developer mode, and availability depends on your plan and workspace. ChatGPT's menus change from time to time, so the labels below may differ slightly from what you see.

### Add the server [#add-the-server]

In ChatGPT's settings, turn on **developer mode**, then add a custom MCP server and point it at:

```text
https://api.orbitorca.com/mcp
```

Choose OAuth as the authentication method if ChatGPT asks.

### Approve the connection [#approve-the-connection]

ChatGPT sends you to an OrbitOrca consent screen that names the connecting app and asks you to grant access:

* **Read** is always granted — the agent can view your resources. It's required to connect.
* **Write** lets the agent create, deploy, and modify your apps. The write tools only work if you grant write here; without it the connection is read-only.

Approve only if you started this from ChatGPT — the connection acts as you. The request expires about 10 minutes after it starts.

### Try it [#try-it]

Ask ChatGPT to *"list my OrbitOrca apps"*. If it comes back with your apps, you're connected.

The connection shows up in your dashboard token list as an **app**, alongside any personal access tokens. Revoke it there the same way — see [Tokens](/docs/mcp/tokens-and-oauth).

Next: [what the approval grants](/docs/mcp/scopes-and-safety).