Backendless Console SDK MCP Server
Enables AI assistants to manage Backendless applications, including databases, users, files, and API services, through natural language commands, with support for OAuth2 authentication and hosted endpoints.
README
Backendless Console SDK MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with programmatic access to Backendless administration and developer APIs.
Backendless MCP enables AI assistants to directly manage your Backendless applications through natural language:
Create a new table called "Products" with columns: name (string), price (number), and inStock (boolean)
List all users who registered in the last 7 days
Your AI assistant can now:
- 1️⃣ Manage databases, users, files, etc.
- 2️⃣ Query data and perform operations
- 3️⃣ All without leaving your development environment
🚀 What is this for?
This MCP server enables AI assistants (like Claude, ChatGPT, Cursor, etc.) to interact with your Backendless applications through the Backendless Console SDK. It exposes a comprehensive set of tools for managing databases, users, API services, cloud code, and other Backendless resources directly from your AI-powered development environment.
Key benefits:
- Direct Backendless integration: Access all Backendless admin APIs through natural language
- Dynamic tool loading: Tools are automatically generated from the Backendless Console SDK
- Secure authentication: Supports OAuth2 authentication
- Flexible usage: Use hosted endpoints
✨ Features
- Comprehensive API coverage: Automatically exposes all available Backendless Console SDK methods as MCP tools
- Session management: Maintains authenticated sessions with Backendless servers
- OAuth2 authentication method:
- Multi-cluster support: Connect to US, EU, local, or Backendless PRO clusters
- Hosted: Use Backendless-provided MCP endpoints (zero setup)
📋 Prerequisites
- Backendless account with API access
📦 Installation
Note: Installation is not required if you're using the Backendless hosted MCP endpoints.
🛠️ Usage
Backendless Hosted MCP (Easiest - Recommended)
Each Backendless cluster provides a hosted MCP server endpoint. This is the easiest way to get started - no installation or server setup required!
Available endpoints:
- US Cluster:
https://develop.backendless.com/mcp - EU Cluster:
https://eu-develop.backendless.com/mcp
<details> <summary><b>Install in Cursor</b></summary>
Go to: Settings → Cursor Settings → MCP → Add new global MCP server
Cursor Hosted Connection
{
"mcp": {
"servers": {
"backendless": {
"type": "http",
"url": "https://develop.backendless.com/mcp"
}
}
}
}
Cursor Local Connection
</details>
<details> <summary><b>Install in Claude Code</b></summary>
Claude Code Hosted Connection
Run this command:
claude mcp add --transport http backendless https://develop.backendless.com/mcp
</details>
<details> <summary><b>Install in VS Code</b></summary>
Add to your VS Code MCP settings. See VS Code MCP docs for more info.
VS Code Hosted Connection
{
"mcp": {
"servers": {
"backendless": {
"type": "http",
"url": "https://develop.backendless.com/mcp"
}
}
}
}
</details>
<details> <summary><b>Install in Windsurf</b></summary>
Add to your Windsurf MCP configuration. See Windsurf MCP docs for more info.
Windsurf Hosted Connection
{
"mcpServers": {
"backendless": {
"serverUrl": "https://develop.backendless.com/mcp"
}
}
}
</details>
<details> <summary><b>Install in Cline</b></summary>
You can easily install Backendless through the Cline MCP Server configuration:
- Open Cline
- Click the hamburger menu icon (☰) to enter the MCP Servers section
- Choose Remote Servers tab
- Click the Edit Configuration button
- Add backendless to
mcpServers:
Cline Hosted Connection
{
"mcpServers": {
"backendless": {
"url": "https://develop.backendless.com/mcp",
"type": "streamableHttp"
}
}
}
</details>
<details> <summary><b>Install in Roo Code</b></summary>
Add this to your Roo Code MCP configuration file. See Roo Code MCP docs for more info.
Roo Code Hosted Connection
{
"mcpServers": {
"backendless": {
"type": "streamable-http",
"url": "https://develop.backendless.com/mcp"
}
}
}
</details>
<details> <summary><b>Install in Claude Desktop</b></summary>
Hosted Connection
Open Claude Desktop and navigate to Settings > Connectors > Add Custom Connector. Enter the name as Backendless and the remote MCP server URL as https://develop.backendless.com/mcp.
</details>
<details> <summary><b>Install in Opencode</b></summary>
Add this to your Opencode configuration file. See Opencode MCP docs for more info.
Opencode Hosted Connection
{
"mcp": {
"backendless": {
"type": "remote",
"url": "https://develop.backendless.com/mcp",
"enabled": true
}
}
}
</details>
<details> <summary><b>Install in Qodo Gen</b></summary>
See Qodo Gen docs for more details.
- Open Qodo Gen chat panel in VSCode or IntelliJ
- Click Connect more tools
- Click + Add new MCP
- Add the following configuration:
Qodo Gen Hosted Connection
{
"mcpServers": {
"backendless": {
"url": "https://develop.backendless.com/mcp"
}
}
}
</details>
<details> <summary><b>Install in Trae</b></summary>
Use the Add manually feature and fill in the JSON configuration information for that MCP server. For more details, visit the Trae documentation.
Trae Hosted Connection
{
"mcpServers": {
"backendless": {
"url": "https://develop.backendless.com/mcp"
}
}
}
</details>
<details> <summary><b>Testing with MCP Inspector</b></summary>
Start your server and test with the MCP Inspector:
# Start the server
BACKENDLESS_HOST=us PORT=3003 npm run start:http
# In another terminal, run the inspector
npx @modelcontextprotocol/inspector
Configure the inspector:
- Transport Type: Streamable HTTP
- URL:
http://localhost:3003/mcp
</details>
🔨 Available Tools
Tools are dynamically loaded from the Backendless Console SDK definitions. The available tools include operations for:
- Data Management: Create, read, update, delete tables and records
- User Management: User registration, authentication, role management
- API Services: Manage and invoke custom API services
- Cloud Code: Deploy and manage server-side business logic
- Files: File upload, download, and management
- Messaging: Push notifications and email management
- Geolocation: Location-based services
- And more: All Backendless Console SDK capabilities
Special Tools
getSDKInfo: Get current SDK session information and status
🔐 Authentication
For Hosted & Self-Hosted HTTP Mode
The server supports OAuth2 authentication method:
OAuth2 Bearer Token: Use standard OAuth2 Bearer authentication
Authorization: Bearer YOUR_TOKEN
When authentication fails, the server responds with a 401 status and WWW-Authenticate header pointing to the OAuth2 discovery endpoints.
🏗️ Architecture
┌─────────────────┐
│ AI Assistant │
│ (Claude, etc.) │
└────────┬────────┘
│ MCP Protocol
│ (HTTP)
▼
┌─────────────────┐
│ MCP Server │
│ (This Package) │
└────────┬────────┘
│ Backendless Console SDK
▼
┌─────────────────┐
│ Backendless │
│ Cluster │
└─────────────────┘
🚨 Troubleshooting
<details> <summary><b>Connection Issues</b></summary>
Symptom: Cannot connect to Backendless cluster
Solutions:
- Check your network connection and firewall settings
- For hosted endpoints, ensure you can access
https://develop.backendless.comorhttps://eu-develop.backendless.comin your browser
</details>
<details> <summary><b>Tool Not Found Errors</b></summary>
Symptom: "Tool not found" errors when trying to use specific operations
Solutions:
- Use
getSDKInfoto check available methods - Ensure you're using the latest version of the MCP server
- Check the Backendless Console SDK version being used
</details>
<details> <summary><b>Port Already in Use</b></summary>
Symptom: "EADDRINUSE" error when starting HTTP server
Solutions:
- Change the
PORTenvironment variable to an available port - Check if another process is using port 3003:
lsof -i :3003(Unix/Mac) ornetstat -ano | findstr :3003(Windows) - Kill the process using the port or choose a different port
</details>
🔗 Links
- Backendless Documentation
- Model Context Protocol
- Backendless Console SDK NPM
- Backendless Console SDK GitHub
📄 License
MIT
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
💬 Support
For issues related to:
- This MCP server or Backendless platform: Backendless Support
- MCP protocol: MCP Documentation
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.