ChatGPT App

Bubbles’ remote MCP server can be added to ChatGPT as a connector, letting ChatGPT read your teams, bubbles, transcripts, and comments — and record a meeting for you — through the tools described in the MCP reference.

Same server, different client

ChatGPT and Claude connect to the same Bubbles MCP endpoint the same way. This page covers the ChatGPT-specific steps; the MCP Server reference has the tool schemas.

Before you start

• The MCP endpoint is your Bubbles API origin followed by /mcp:

  https://api.usebubbles.com/mcp

• Adding a connector in ChatGPT currently requires developer mode (Settings → Connectors → Advanced → Developer mode), which lets you add a custom MCP server by URL.

• Connecting takes no setup: ChatGPT registers itself automatically (dynamic client registration) and runs the OAuth handshake for you. There is no token to paste. You sign in once in your browser and approve the access ChatGPT is asking for, then you are returned to the conversation.

Add Bubbles in ChatGPT

1. In ChatGPT, open Settings → Connectors. Enable Developer mode under Advanced if you don’t already see the option to add a custom connector.

2. Choose Add custom connector (MCP server) and paste your MCP endpoint URL:

   https://api.usebubbles.com/mcp

3. ChatGPT opens Bubbles in your browser. Sign in (or create an account) and approve the access ChatGPT is asking for — you are returned to ChatGPT with the connector ready.

4. Start a chat and enable the Bubbles connector.

Sign in

A newly added connector is not signed in yet: ChatGPT can see the Bubbles tools, but the ones that read your data return a short “not signed in” message with no data until you sign in. There is no token to copy — sign-in happens in your browser, once:

1. Adding the connector opens Bubbles in your browser. Sign in, or create an account — the same page handles both.

2. Approve the access ChatGPT is asking for. You are returned to your conversation, signed in on that connection.

3. If you’re new, the browser sign-up already walks you through the workspace step — joining one your email domain uses, or creating your own. You come back to ChatGPT fully set up.

Your Bubbles workspace needs a paid plan

Approving access requires a workspace with paid-feature access. On a free workspace the approval step returns pro_required and the consent screen asks you to upgrade — upgrade in Bubbles, then connect again.

Once you’re signed in, the read tools return your data and join_meeting works. ChatGPT remembers the connection, so a new conversation is already signed in.

What ChatGPT can do once connected

The same six read-only tools (full schemas in the MCP reference):

• list_bubbles, search_bubbles, get_bubble, get_bubble_transcript, get_bubble_comments, list_teams.

plus one write tool:

• join_meeting — send the Bubbles notetaker to join and record a meeting by link. It uses the meetings:join permission your connection carries and is used only when you explicitly ask ChatGPT to record a meeting.

With the read tools ChatGPT can read your bubbles but cannot create, edit, or delete anything — and it only ever sees bubbles you can read in the product.

Review / availability status

Pending

Bubbles is not yet published as a reviewed ChatGPT app. Public app availability requires OpenAI organization verification and app review (tracked as an owner action). In the meantime, developer mode lets you add and use the Bubbles connector directly with the URL above.

Troubleshooting

• No “Add custom connector” option — enable Developer mode in Settings → Connectors → Advanced.
• Discovery / connection fails — confirm you pasted your Bubbles MCP endpoint (https://api.usebubbles.com/mcp) exactly, and that it is reachable over the public internet (ChatGPT connects from OpenAI’s cloud, not your device).
• Tools return “not signed in” — the browser sign-in and approval did not complete. Reconnect the connector and finish the Bubbles sign-in, approving the access ChatGPT asks for.
• A tool returns nothing after sign-in — you only see bubbles you can read in the product; the same access rules apply to the API and MCP.