Connect Contextick to ChatGPT

ChatGPT can use Contextick, but it asks more of you than the other options: a paid plan, a developer mode setting you turn on yourself, and a confirmation click each time it saves something. Here's the whole path, honestly.

Coming soon: one-click install. Contextick is under review for ChatGPT's official directory. Once it's approved, you'll search for Contextick there and add it in one click — no developer mode required. If the steps below look like more than you want to do today, Claude connects on its free plan in about a minute.

What you'll need

• A paid ChatGPT plan. Developer mode is available on Plus, Pro, Business, Enterprise, and Education — not on Free.
• ChatGPT on the web or the desktop app. You can't add a connector from the mobile app — set it up on a computer. Once it's connected, that's a one-time thing.
• Developer mode turned on, which you do yourself in settings (step 1 below). On Business, Enterprise, and Education, a workspace owner may need to allow it first.
• A Contextick account. You'll sign in with Google during the connection, so no API key is needed — ChatGPT's web connectors use OAuth and don't accept a pasted key.

One thing to expect: ChatGPT asks you to confirm before an action that writes data. So each time you ask it to save something to Contextick, you'll get a confirmation prompt. That's ChatGPT's behaviour, not something we can turn off — you can approve a tool for the rest of a conversation to cut down on the clicking.

Steps

1. In ChatGPT, open Settings → Security and login and turn on Developer mode.
2. Open Settings → Plugins (or go straight to chatgpt.com/plugins).
3. Click the + button to create a developer mode app for a remote MCP server.
4. Name it Contextick, paste https://contextick.ai/mcp as the MCP server URL, and choose OAuth as the authentication method.
5. Save. ChatGPT sends you to Contextick to sign in with Google and approve access.
6. Contextick is now available in ChatGPT. Enable it for a conversation from the composer's tools menu.

Check it worked

Test it in two parts, and make the second part a new chat. If you ask in the same conversation, ChatGPT can answer from what you just said without ever calling Contextick — so a broken connection would still look like it worked.

1. Save something you'd actually want back. At the end of a conversation where you worked something out, say: "Save what we landed on for the kitchen renovation budget to Contextick." Confirm when ChatGPT asks — that's the write confirmation.
2. Open a new chat with Contextick enabled and ask: "What did we land on for the kitchen renovation budget?"

If it comes back in the new chat, you're connected — and you've just seen the point of it: you didn't have to explain any of it again. Anything you save here is available in Claude or any other AI you connect to Contextick.

If it doesn't show up

• You can't find Developer mode. It isn't on the Free plan. On a Business, Enterprise, or Education workspace, an owner has to allow it before you'll see the toggle.
• ChatGPT never offers Contextick. Enable it for the conversation from the tools menu in the composer, then ask it directly — "save this to Contextick".
• Saving does nothing. Look for the confirmation prompt — writes wait on your approval, and it's easy to miss.
• Deep research or agent mode can't see it. Those modes handle custom connectors differently. Use a normal chat.

Official docs

OpenAI's own guide: Developer mode. ChatGPT's connector features are rolling out and changing, so if a screen here doesn't match what you see, their docs are the place to check.