CloudBase MCP

v2.19.5Cloud Servicesstable

Bridges AI IDEs with Tencent CloudBase for seamless deployment, enabling users to go from AI-generated code to live applications with automatic cloud resource configuration, database setup, and intelligent debugging.

aiaicodingcloudbasecursormcp
Share:
1,015
Stars
0
Downloads
0
Weekly
0/5

What is CloudBase MCP?

CloudBase MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to bridges ai ides with tencent cloudbase for seamless deployment, enabling users to go from ai-generated code to live applications with automatic cloud resource configuration, database setup, and intell...

Bridges AI IDEs with Tencent CloudBase for seamless deployment, enabling users to go from AI-generated code to live applications with automatic cloud resource configuration, database setup, and intelligent debugging.

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Bridges AI IDEs with Tencent CloudBase for seamless deployme

Use Cases

Deploy AI-generated code to Tencent CloudBase
Serverless and database auto-configuration
LicenseMIT
Languagetypescript
Versionv2.19.5
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @cloudbase/cloudbase-mcp

Manual Installation

npx -y @cloudbase/cloudbase-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use CloudBase MCP

CloudBase MCP bridges AI coding environments like Cursor, Claude Code, and WindSurf with Tencent CloudBase's serverless platform, letting you deploy complete full-stack applications through natural language instructions. It automates the entire deployment pipeline: generating code, configuring cloud databases, creating serverless functions, setting up static hosting, and returning live URLs — all without leaving your AI IDE. Teams building WeChat Mini Programs or serverless web apps on Tencent Cloud get a zero-friction path from AI-generated prototype to production deployment.

Prerequisites

  • Node.js v18.15.0 or higher
  • A Tencent Cloud account with an active CloudBase environment (env_id)
  • Tencent Cloud SecretId and SecretKey for authentication
  • An MCP-compatible AI IDE: Cursor, WindSurf, Claude Desktop, or Claude Code
  • Optional: Tencent CloudBase CLI (npm install -g @cloudbase/cli) for local login
1

Create a Tencent CloudBase environment

Log in to the Tencent CloudBase console and create a new environment. Note the environment ID (env_id) — you will need it for the hosted mode configuration.

2

Install CloudBase MCP via npx

Run the CloudBase MCP server directly with npx. No global installation is required; npx will pull the latest version automatically.

npx -y @cloudbase/cloudbase-mcp@latest
3

Add to your MCP client configuration (local mode)

Add CloudBase MCP to your Claude Desktop or Cursor config file. Local mode is recommended for development as it uses your CLI login credentials.

{
  "mcpServers": {
    "cloudbase": {
      "command": "npx",
      "args": ["-y", "@cloudbase/cloudbase-mcp@latest"]
    }
  }
}
4

Or configure hosted mode with API keys

For production or team use, configure the hosted HTTP mode by providing your Tencent Cloud credentials and CloudBase environment ID in the headers.

{
  "mcpServers": {
    "cloudbase": {
      "type": "http",
      "url": "https://tcb-api.cloud.tencent.com/mcp/v1?env_id=YOUR_ENV_ID",
      "headers": {
        "X-TencentCloud-SecretId": "YOUR_SECRET_ID",
        "X-TencentCloud-SecretKey": "YOUR_SECRET_KEY"
      }
    }
  }
}
5

Login via CLI for local mode

If using local mode, authenticate the CloudBase CLI so the MCP server can access your cloud resources without needing inline credentials.

npm install -g @cloudbase/cli@latest
tcb login
6

Start building and deploying with natural language

With the MCP server connected, you can describe what you want to build in plain English and CloudBase MCP will handle database setup, cloud functions, and deployment automatically.

CloudBase MCP Examples

Client configuration

Local mode MCP configuration for Claude Desktop — the recommended setup for development with CloudBase MCP.

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

Prompts to try

Example prompts that demonstrate CloudBase MCP's ability to build and deploy complete applications end-to-end.

- "Build a two-player online gomoku game with WebSocket support and deploy it to CloudBase"
- "Create a REST API for a todo app with a CloudBase database and deploy the cloud functions"
- "Upload my static site files to CloudBase hosting and configure a custom domain"
- "Show me the logs for my cloud function named user-auth"

Troubleshooting CloudBase MCP

Authentication fails with 'SecretId/SecretKey invalid'

Verify your Tencent Cloud SecretId and SecretKey are correct in the CAM console. Ensure the sub-account has CloudBase permissions. For local mode, run 'tcb login' to refresh credentials.

Deployment fails with 'environment not found'

Double-check the env_id in your configuration matches an existing CloudBase environment in your Tencent Cloud account. The env_id is visible in the CloudBase console dashboard.

npx command hangs or fails to download the package

Try specifying the version explicitly: 'npx -y @cloudbase/cloudbase-mcp@latest'. If behind a corporate proxy, set HTTP_PROXY and HTTPS_PROXY environment variables before running npx.

Frequently Asked Questions about CloudBase MCP

What is CloudBase MCP?

CloudBase MCP is a Model Context Protocol (MCP) server that bridges ai ides with tencent cloudbase for seamless deployment, enabling users to go from ai-generated code to live applications with automatic cloud resource configuration, database setup, and intelligent debugging. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install CloudBase MCP?

Install via npm with the command: npx -y @cloudbase/cloudbase-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with CloudBase MCP?

CloudBase MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is CloudBase MCP free to use?

Yes, CloudBase MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use CloudBase MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides