How to Connect Bubble to Microsoft Copilot 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 + Microsoft Copilot

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 Microsoft Copilot

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.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Bubble tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

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

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

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