Tencent CloudBase MCP server for AI agents

CloudBase AI ToolKit is an MCP (Model Context Protocol) server that enables AI-assisted development with Tencent CloudBase. It allows you to automatically generate, deploy, and host full-stack web applications, mini programs, databases, and backend services.

Getting Started with CloudBase MCP Server

CloudBase MCP server integrates with AI coding tools to provide seamless deployment to Tencent CloudBase. This integration helps you quickly develop and deploy applications without managing infrastructure.

Prerequisites

Before using the CloudBase MCP server, ensure you have:

Node.js v18.15.0 or higher installed
An AI development tool (Cursor, VSCode with GitHub Copilot, WindSurf, CodeBuddy, etc.)
A Tencent CloudBase environment (can be created for free at the Tencent CloudBase Console)

Installation

Install the CloudBase MCP server in your project by adding it to your AI development tool's MCP configuration:

npx @cloudbase/cloudbase-mcp@latest

Configuration

Configuring MCP in Your AI Tool

Depending on which AI coding tool you use, you'll need to add the CloudBase MCP configuration to your project.

For Cursor:

Add the following to .cursor/mcp.json:

{
  "mcpServers": {
    "cloudbase-mcp": {
      "command": "npx",
      "args": ["@cloudbase/cloudbase-mcp@latest"]
    }
  }
}

For GitHub Copilot:

Add the following to .vscode/mcp.json:

{
    "servers": {
        "cloudbase": {
            "command": "npx",
            "args": [
                "@cloudbase/cloudbase-mcp@latest"
            ]
        }
    }
}

For WindSurf/Codeium:

Add this to your WindSurf Plugins configuration:

{
  "mcpServers": {
    "cloudbase-mcp": {
      "command": "npx",
      "args": ["@cloudbase/cloudbase-mcp@latest"]
    }
  }
}

For Other AI Tools:

Most AI coding tools support similar configuration patterns. Add the CloudBase MCP server with:

{
  "mcpServers": {
    "cloudbase": {
      "command": "npx",
      "args": ["@cloudbase/cloudbase-mcp@latest"]
    }
  }
}

Using CloudBase MCP

Once you've configured the MCP server, you can start using it with simple commands in your AI tool:

Authentication

login to CloudBase

The AI will help you authenticate with Tencent CloudBase and select an environment.

To logout:

logout from CloudBase

Environment Information

Query your current CloudBase environment:

query current CloudBase environment information

Development Workflow

Describe your project needs to the AI:

Create a multiplayer online chess game with real-time updates

The AI will:
- Generate the necessary code
- Deploy it to CloudBase
- Provide you with access links
Debugging: If you encounter errors, share them with the AI:

I'm getting an error: [error message]

The AI can analyze CloudBase function logs and help debug issues:

The cloud function isn't working as expected. Please check the logs and fix it.

Plugin System

CloudBase MCP uses a plugin architecture to provide tools for different aspects of development. Enable specific plugins by configuring environment variables:

{
  "env": {
    "CLOUDBASE_MCP_PLUGINS_ENABLED": "env,database,functions,hosting"
  }
}

Available plugins include:

env: Environment management
database: Database operations
functions: Cloud function management
hosting: Static site hosting

Advanced Configuration

Disabling Telemetry

You can disable anonymous usage statistics by setting:

{
  "env": {
    "CLOUDBASE_MCP_TELEMETRY_DISABLED": "true"
  }
}

NPX Cache Issues

If you encounter installation problems related to npx caching:

npx clear-npx-cache

Troubleshooting

If tools show as quantity 0 after installation:

Restart your AI IDE
Disable and re-enable the CloudBase MCP
Check your network connection to ensure the MCP server can be downloaded

For more troubleshooting help, refer to the FAQ documentation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "cloudbase-mcp" '{"command":"npx","args":["-y","@cloudbase/cloudbase-mcp@latest"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cloudbase-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "@cloudbase/cloudbase-mcp@latest"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "cloudbase-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "@cloudbase/cloudbase-mcp@latest"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect