OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Cloudbase AI Toolkit

Cloudbase AI Toolkit is an open-source integration toolkit that connects AI coding tools to CloudBase backend services. Its plugin installs integration components, agent skills guide CloudBase-aware code generation, and an MCP server supports chat-driven operations on databases, functions, storage and deployments.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cloudbase AI Toolkit — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an AI coding tool needs both CloudBase-specific code guidance and a connection to backend resources in a CloudBase environment.

Who it is for

  • Developers using AI coding tools to build applications backed by CloudBase.
  • Teams that want an AI coding workflow to combine backend-aware code guidance with conversational resource operations.

Documented uses

  • Connect an AI coding environment to a CloudBase backend.
  • Guide generated application code toward CloudBase practices using agent skills.
  • Query or change data and manage functions, hosting and deployment-related tasks from an AI conversation.
  • Read backend logs while working through a coding workflow.
Before you choose

Requirements & limits

The toolkit is an MIT-licensed public GitHub repository. Its documentation describes local MCP and remote HTTP connection modes; remote interactive authorization uses browser login and consent.

  • The plugin, agent skills and MCP server have different roles: integration setup, code guidance and backend operations, respectively.
  • Remote MCP avoids local Node installation; local MCP is documented with local filesystem upload and template-download capabilities.
  • The remote endpoint must match the CloudBase site for the environment; domestic and international sites use separate accounts and credentials.
  • The toolkit requires a CloudBase environment, and the project advises checking sensitive actions proposed by the AI.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Connect an AI coding tool with local MCP

Add the CloudBase MCP server to an MCP-capable coding tool using the documented local configuration.

Before you start

  • An MCP-capable AI coding tool
  • A CloudBase environment
  • Node and npx available for the local server command

Steps

  1. Add an MCP server entry named cloudbase to the coding tool’s MCP configuration.

  2. Set its command to npx and its argument to @cloudbase/cloudbase-mcp@latest.

  3. Use the configured assistant to log in to CloudBase, then review proposed sensitive actions.

Expected outcome

The coding tool can connect to CloudBase through the local MCP server for chat-driven backend work.

Guide limitations

  • The instructions do not specify supported versions for every coding tool.
  • A CloudBase environment is still required; AI-proposed sensitive actions should be checked.
Documentation 1 ↗
Source-based practical guide

Connect through remote MCP with OAuth

Configure a remote CloudBase MCP endpoint so an interactive coding tool can authorize through a browser.

Before you start

  • An interactive MCP-capable AI coding tool
  • A CloudBase environment and the matching domestic or international site

Steps

  1. Choose the remote MCP endpoint matching the site where the CloudBase environment resides.

  2. Add the endpoint URL to the coding tool’s MCP configuration without static keys.

  3. Complete the browser-based login and consent flow when prompted.

Expected outcome

The coding tool connects to the remote MCP service after interactive authorization.

Guide limitations

  • The two CloudBase sites use separate accounts, consoles and credentials.
  • The documented flow requires an interactive client; static credentials are described separately for CI/CD.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Cloudbase AI ToolkitConnect an AI coding environment to a CloudBase backend.CLI, Cloud, ServerThe toolkit is an MIT-licensed public GitHub repository. Its documentation describes local MCP and remote HTTP connection modes; remote interactive authorization uses browser login and consent.
OvertureInspect a coding agent’s planned steps and branches before code is written.Self-hosted, Server, WebOpen-source software under the MIT license. The documented setup runs the MCP server locally and opens its web interface at `http://localhost:3031` by default.
WigoloSearch the web and fetch pages for an agent’s research task.CLI, Self-hosted, ServerThe quickstart lists macOS, Linux and Windows, and requires Node.js 20 or later with about 1.5 GB of free disk space. The repository labels the project public beta.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
TencentCloudBase/CloudBase-AI-Toolkit · Official homepage title · retained in its source language
How we review sourcesSuggest a correction