Verified

Cloudbase AI Toolkit MCP Server

Tencent CloudBase backend services managed directly through MCP server tools.

Data last scanned today · Reviewed today

283 dangerous tools43 tools1,104TypeScriptMIT

Overview

CloudBase AI Toolkit serves as an integration layer connecting AI coding assistants to Tencent CloudBase backend infrastructure. It enables direct management of databases, storage, cloud functions, and environment deployments from within chat interfaces. The toolkit streamlines development by bundling MCP server implementation, agent skills, and environment hooks. Developers can use it to handle cloud API operations, monitor services, and execute declarative deployment plans without manual switching.

Our verdict

With a security score of 53/100, this tool is categorized as high risk. Because the authentication method has not yet been reviewed and the server lacks an independent security audit, it is recommended only for development environments rather than production-sensitive workflows. Users should exercise caution when granting access to cloud-native backend infrastructure.

  • Supports declarative deployment plans via deployApply.
  • Simplifies cross-IDE setup with bundled plugins and skills.
  • Maintains an active development cycle with daily commits.
  • Includes centralized error guidance for cloud function deployment.
  • Security architecture lacks verified authentication method review.
  • Community-maintained status requires extra diligence for critical infrastructure tasks.
  • Read-only mode implementation status remains unverified.

Setup

Claude Desktop
{
  "mcpServers": {
    "cloudbase-ai-toolkit": {
      "args": [
        "-y",
        "cloudbase-ai-toolkit"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

  • No read-only mode — running this grants full read/write access.
  • No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

ToolDescriptionRisk
authCloudBase (Tencent CloudBase) development stage login and environment binding.medium
queryEnvQuery environment details.low
manageEnvManage environments.medium
deployBuildPerform deployment build.medium
deployPlanPlan deployment.medium
deployApplyApply deployment configuration.medium
queryAppsQuery applications.low
manageAppsManage applications.medium
envQueryQuery environment.low
envDomainManagementManage environment domains.medium

Compatibility

ClientLocalDockerRemoteRead-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

What are the prerequisites for using this MCP server?

You must have your own active CloudBase environment and an AI IDE such as Claude Code, Codex, or Cursor.

How do I install the MCP server?

The server can be installed using the command npx @cloudbase/cloudbase-mcp@latest, or by following the instructions in the project's skill.md file via your AI IDE.

Can I use multiple installation methods simultaneously?

No, if you are using the MCP server via a marketplace IDE, you should not also run the npx plugins add command on the same tool.

How is environment configuration handled?

You can use a cloudbaserc.json file to provide field-level fallbacks for your environment ID, region, and site settings.

What permissions or security considerations should I keep in mind?

The toolkit provides backend capabilities but does not perform judgment on actions; you should confirm any sensitive actions proposed by the AI.

Alternatives

Changelog

Badge

Cloudbase AI Toolkit MCP Server security score, rated on RepoAI

Maintain this server? Add the live badge to your README.