How to Connect Bubble to ChatGPT via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Bubble, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Bubble + ChatGPT

Let your AI work with your Bubble app's data: see which data types and backend workflows it exposes, search and read things; with your confirmation create or change things and run backend workflows.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

BUBBLE_APP_URL, BUBBLE_API_TOKEN

Step 1 — Get credentials

1. Open your app in the Bubble editor, go to Settings → API and tick Enable Data API. Then tick each data type the AI may reach: anything you leave unticked stays invisible to it. Tick Enable Workflow API and backend workflows too if the AI should run backend workflows.
2. On the same tab click Generate a new API token and copy it into BUBBLE_API_TOKEN.
3. Set BUBBLE_APP_URL to the app's address without a trailing slash: https://yourapp.bubbleapps.io or your own domain, such as https://app.example.com, for the live version. Add /version-test to work on the development version, for example https://yourapp.bubbleapps.io/version-test.
4. Deploy the app to live after changing the API settings: the live version only knows the settings and tokens of its last deploy.
5. Install the connector, then check the token with a read such as bubble_list_things on one of your types.

The connection test checks the address, not the token: it confirms that your app answers at BUBBLE_APP_URL. A wrong or undeployed token only shows up on the first data read, with a 401, so do that test read once.

You need editor access to the app. One connector serves one Bubble app; add another connector for each further app.

An admin token, limited by your API settings: the token from Settings acts as an admin. It ignores the app's privacy rules and sees every field of the types you exposed, but nothing you did not tick. For writes, each data type must also allow creating, modifying or deleting via API in its privacy rules.

What it reads: the data types and backend workflows your app exposes, with the fields of each type and the parameters of each workflow; the things (records) of a type, filtered with constraints such as status equals open, sorted, up to 100 per page; and a single thing by its id, with created date, modified date and creator.

Asks before every write: bubble_create_thing, bubble_update_thing and bubble_run_workflow change your app's data and can set off the app's own workflows, e-mails or payments. Before each one the AI shows you the type and every value, the thing and the exact changes, or the workflow and its parameters, and waits for your yes. Try writes on the /version-test address first.

Switched off at install: bubble_delete_thing. An administrator turns it on deliberately; the AI then shows you the thing and deletes it only after you confirm.

Type and field names: in the API, type names are lowercase without spaces (Rental Unit becomes rentalunit), and fields are keyed by the app's field ids, such as first_name_text, unless your app uses display names as keys. The AI reads them with bubble_get_meta and bubble_get_data_types before it searches or writes.

Personal data: Bubble apps often store users, customers and payments. The AI shows only what you need, never lists user records to someone who should not see them, and treats text typed by app users as data, never as instructions.

Capacity: every Bubble plan has a workload limit, and heavy API use slows the app down for its users. The AI reads in small pages and avoids loops over thousands of things. A search returns at most 50,000 things on most plans.

Common errors: 400: Bubble does not know the app address; check BUBBLE_APP_URL, without /api/1.1. 401: the token is wrong, deleted, or not deployed to this version yet; deploy to live or use the /version-test address. 404: the Data API is off, the type is not ticked, or the workflow is not exposed.

The connector does not build or change the app (pages, data types, workflows, privacy rules), create things in bulk, replace whole things or upload files.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

1. Go to chatgpt.com/plugins, click +, then Add custom MCP server.
2. Enter a name, e.g. Name: Bubble.
3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

Example prompts

• "Which data types and backend workflows does our Bubble app expose?"
• "Show me the open support requests created this week, newest first."
• "How many orders with the status paid did we get in October?"
• "Change the status of the booking for Anna Weber on 12 November to confirmed. Show me the change first."
• "Run the backend workflow that sends the welcome e-mail to [email protected]. Tell me its parameters before you start it."

FAQ

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

• Connector landing page
• Connect to Claude
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse