Bubble MCP
Enables AI assistants to interact with Bubble.io applications through the Model Context Protocol for data discovery, CRUD operations, and workflow execution. It provides a standardized interface for managing Bubble database records while respecting privacy rules and security configurations.
README
Bubble MCP
A Model Context Protocol (MCP) server that enables AI assistants and other MCP-compatible clients to interact with Bubble.io applications. This server provides a standardized interface for reading and manipulating data in any Bubble application.
🚀 Features
- Universal Bubble Support: Works with any Bubble.io application
- Auto-discovery: Automatically discovers your app's data types and structure
- CRUD Operations: Create, Read, Update, and Delete operations for all data types
- Workflow Execution: Execute API workflows defined in your Bubble app
- Privacy Settings Aware: Respects Bubble's privacy rules and constraints
- Read-only/Read-write Modes: Configurable access levels for safety
- Type-safe: Provides detailed type information for all operations
🔌 MCP Compatibility
This server implements the Model Context Protocol (MCP), an open protocol that enables secure, standardized communication between AI assistants and external systems. While MCP was developed by Anthropic, it's designed to be vendor-agnostic.
Currently Compatible Clients:
- Claude Desktop - Full support
- Other MCP clients - Should work with any client that implements the MCP specification
Future Compatibility:
As MCP is an open protocol, we expect more AI assistants and tools to add support over time. This server will work with any client that properly implements the MCP standard.
📋 Prerequisites
- Node.js (v16 or higher)
- npm or yarn
- A Bubble.io application with API access enabled
- An MCP-compatible client (e.g., Claude Desktop)
🛠️ Installation
Local Development Setup
For Mac/Linux:
-
Clone the repository:
git clone https://github.com/nocoderoi/bubble_mcp.git cd bubble_mcp -
Install dependencies:
npm install -
Copy the example environment file:
cp .env.example .env -
Edit
.envwith your Bubble app details:nano .env # or use your preferred text editor -
Build the project:
npm run build
For Windows:
-
Clone the repository:
git clone https://github.com/nocoderoi/bubble_mcp.git cd bubble_mcp -
Install dependencies:
npm install -
Copy the example environment file:
copy .env.example .env -
Edit
.envwith your Bubble app details:notepad .envOr use any text editor to add:
BUBBLE_BASE_URL=https://your-app.bubbleapps.io BUBBLE_API_TOKEN=your-bubble-api-token-here MCP_MODE=read-write # Options: read-only, read-write -
Build the project:
npm run build
🔧 Configuration
Getting Your Bubble API Token
- Go to your Bubble app editor
- Navigate to Settings → API
- Enable "This app exposes a Data API"
- Generate an API token
- Copy the token to your
.envfile
Setting Up Your MCP Client
The exact configuration steps depend on your MCP client. Below are examples for Claude Desktop:
Claude Desktop Configuration
For Mac/Linux:
-
Copy the example configuration:
cp claude-desktop-config.example.json claude-desktop-config.json -
Edit
claude-desktop-config.jsonwith your absolute path:pwd # Get your current directory path nano claude-desktop-config.json -
Update the configuration (example for Mac/Linux):
{ "mcpServers": { "bubble": { "command": "node", "args": [ "/Users/yourname/projects/bubble_mcp/dist/mcp-server.js" ], "env": { "BUBBLE_BASE_URL": "https://your-app.bubbleapps.io", "BUBBLE_API_TOKEN": "your-bubble-api-token-here", "MCP_MODE": "read-write" } } } } -
Copy to Claude Desktop config location:
cp claude-desktop-config.json ~/Library/Application\ Support/Claude/claude_desktop_config.json
For Windows:
-
Copy the example configuration:
copy claude-desktop-config.example.json claude-desktop-config.json -
Get your current directory path:
cd -
Edit
claude-desktop-config.jsonwith the full Windows path:{ "mcpServers": { "bubble": { "command": "node", "args": [ "C:\\Users\\yourname\\projects\\bubble_mcp\\dist\\mcp-server.js" ], "env": { "BUBBLE_BASE_URL": "https://your-app.bubbleapps.io", "BUBBLE_API_TOKEN": "your-bubble-api-token-here", "MCP_MODE": "read-write" } } } }Note: Use double backslashes (
\\) in the path! -
Copy to Claude Desktop config location:
copy claude-desktop-config.json %APPDATA%\Claude\claude_desktop_config.json -
Restart Claude Desktop
Other MCP Clients
For other MCP-compatible clients, refer to their documentation for configuration instructions. The key configuration elements you'll need are:
- Command:
node - Arguments: Path to
dist/mcp-server.js - Environment variables:
BUBBLE_BASE_URL,BUBBLE_API_TOKEN, andMCP_MODE
🎯 Usage
Once configured, you can interact with your Bubble app through your MCP client:
Available Commands
- List Data Types: "Show me all data types in my Bubble app"
- Fetch Records: "Get all users from my database"
- Create Records: "Create a new user with name 'John Doe'"
- Update Records: "Update user with ID xxx to set email to 'new@email.com'"
- Delete Records: "Delete the product with ID xxx"
- Execute Workflows: "Run the 'send_welcome_email' workflow for user xxx"
🎥 Video Example
Watch a video demonstration of how to use the Bubble MCP integration with Claude Desktop:
Example Interactions
You: "List all the data types in my Bubble app"
Assistant: I'll help you discover the data types in your Bubble app...
You: "Show me the first 5 customers"
Assistant: I'll fetch the first 5 customers from your database...
You: "Create a new product called 'Widget' with price 29.99"
Assistant: I'll create a new product for you...
🔒 Security Considerations
Understanding MCP Modes
The Bubble MCP server supports two operational modes that control what actions the MCP client can perform:
🔍 Read-Only Mode (Recommended)
- What it does: Only allows viewing and fetching data from your Bubble app
- Available operations:
- List data types
- Fetch records
- View app structure
- Blocked operations: Create, Update, Delete, and Workflow execution
- When to use:
- When exploring your data
- For reporting and analysis
- When learning about your app structure
- As your default setting for safety
✏️ Read-Write Mode
- What it does: Allows full CRUD operations and workflow execution
- Available operations: All read operations PLUS:
- Create new records
- Update existing records
- Delete records
- Execute API workflows
- When to use:
- Only when you specifically need to modify data
- For automation tasks
- During active development
🛡️ Best Practices for Safety
-
Start with Read-Only: Always begin with
MCP_MODE=read-onlyin your configuration"env": { "MCP_MODE": "read-only" // Safe default } -
Temporary Write Access: Only switch to
read-writewhen you need to perform modifications"env": { "MCP_MODE": "read-write" // Use with caution } -
Separate Configurations: Consider having two MCP server configurations:
bubble-readonly: Your default for everyday usebubble-write: Only for when modifications are needed
-
API Token Permissions:
- Create separate API tokens with different permission levels
- Use restricted tokens for read-only access
- Keep write-enabled tokens extra secure
⚠️ Mode Differences at a Glance
| Feature | Read-Only | Read-Write |
|---|---|---|
| List data types | ✅ | ✅ |
| Fetch records | ✅ | ✅ |
| Create records | ❌ | ✅ |
| Update records | ❌ | ✅ |
| Delete records | ❌ | ✅ |
| Execute workflows | ❌ | ✅ |
| Risk of data loss | None | Possible |
| Recommended for beginners | ✅ | ❌ |
🔐 Additional Security Tips
- API Tokens: Never commit your API tokens to version control
- Environment Variables: Always use environment variables or secure configuration for sensitive data
- Privacy Rules: The server respects Bubble's privacy rules - ensure your API token has appropriate permissions
- Audit Trail: In read-write mode, keep track of changes made through the MCP server
- Backup: Always backup your Bubble data before using read-write mode for bulk operations
🤝 Contributing
We welcome contributions from the community! Here's how you can help:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Development Guidelines
- Write clear, commented code
- Add tests for new features
- Update documentation as needed
- Follow the existing code style
- Test with different Bubble app configurations
🐛 Troubleshooting
Common Issues
- "Cannot find data type": Ensure your Bubble app has the Data API enabled
- "Authentication failed": Check your API token is correct and has appropriate permissions
- "Privacy rule violation": Your API token may not have access to certain data types
- MCP client not connecting: Ensure the path in config is absolute and the server is built
Starting the Server
To start the MCP server, use one of the following commands depending on your environment:
For Direct Node Execution:
node dist/mcp-server.js
For Development Mode (with hot-reloading):
npm run mcp
Debug Mode
Set DEBUG=true in your environment to enable verbose logging:
Mac/Linux:
DEBUG=true npm run mcp
Windows (Command Prompt):
set DEBUG=true && npm run mcp
Windows (PowerShell):
$env:DEBUG="true"; npm run mcp
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
Made with ❤️ by the community
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.
