Log inSubmit server
CloudBase AI ToolKit logo

CloudBase AI ToolKit

by TencentCloudBase

Connects AI coding tools to CloudBase for database, function, storage, hosting, gateway, and deployment operations.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install CloudBase AI ToolKit

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "tencentcloudbase-cloudbase-ai-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "@cloudbase/cloudbase-mcp@latest"
      ],
      "env": {
        "TENCENTCLOUD_SECRETID": "YOUR_VALUE_HERE",
        "TENCENTCLOUD_SECRETKEY": "YOUR_VALUE_HERE",
        "TCB_TCR_USERNAME": "YOUR_VALUE_HERE",
        "TCB_TCR_PASSWORD": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

The TencentCloudBase/CloudBase-AI-ToolKit MCP server connects AI coding tools to Tencent CloudBase environments through MCP tools for authentication, resource discovery, databases, functions, storage, hosting, and deployment. It supports both read-only inspection and confirmed changes, including PostgreSQL, NoSQL, MySQL, cloud functions, static hosting, Cloud Run, HTTP gateways, and project-level deployments. Use it when an agent needs to inspect or operate a CloudBase backend from an IDE conversation, while retaining an existing CloudBase environment and credentials. Local MCP modes can also use project files for builds and declarative deployment workflows.

Use cases

  • Inspect CloudBase environments and resource usage
  • Query and manage NoSQL or PostgreSQL data
  • Deploy cloud functions and configure triggers
  • Publish static sites and configure gateway routes
  • Plan and apply cloudbaserc project deployments

Key features

  • CloudBase authentication and environment binding
  • NoSQL, PostgreSQL, and MySQL database operations
  • Cloud function deployment, logs, versions, and triggers
  • Static hosting, storage, Cloud Run, and gateway management
  • Template download and CloudBase documentation search
  • Declarative deployment planning and execution

Tools42

What CloudBase AI ToolKit lets your agent do. Expand a tool for its parameters.

Verified live~29.4k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

30/31 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9d ago via OSV.dev · @cloudbase/cloudbase-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1.2kStargazers on the source repository.
npm downloads28kPackage downloads in the last 30 days.
Last commitTodayMost recent push to the default branch.
Tools exposed42Callable tools this server registers over MCP.
Directory activity11 viewsConfig copies, upvotes, and views on AllMCPs.

How CloudBase AI ToolKit works

What TencentCloudBase/CloudBase-AI-ToolKit does

The TencentCloudBase/CloudBase-AI-ToolKit MCP server exposes Tencent CloudBase backend operations to MCP-compatible AI coding tools. It connects an agent to a selected CloudBase environment and provides tools for inspecting and changing backend resources from a conversation.

The repository includes the MCP server package, agent skills, and plugin-related configuration. The MCP layer covers authentication, environment selection, databases, functions, storage, static hosting, cloud-hosted services, HTTP gateways, templates, documentation search, and deployment workflows. A CloudBase environment is still required; the toolkit does not replace the account, environment, or permission model.

How it works

Authentication can use CloudBase login or an API key. After login, the agent binds an environment with set_env; most other tools depend on that binding. Environment queries distinguish account-level credentials from environment-level credentials, so an environment-level key may only return its permitted envId rather than all regional environments.

Read operations are separated from write operations in many areas. For example, queryFunctions reads function metadata and logs, while manageFunctions creates functions, updates code, publishes versions, configures aliases, and manages triggers. Similar query/manage pairs exist for hosting, storage, Cloud Run, and gateways.

Sensitive operations use explicit confirmation rules. Environment creation, plan changes, renewals, destructive SQL, deletes, and deployments require confirmation parameters or an approval step. Declarative deployments use deployPlan to calculate changes and deployApply to execute a reviewed plan from cloudbaserc.

Setup and configuration

The TencentCloudBase/CloudBase-AI-ToolKit MCP server can be started from the published package with npx @cloudbase/cloudbase-mcp@latest, according to the repository’s quick-start material. MCP-capable IDEs can use the server configuration directly; the repository also documents plugin and marketplace paths for supported tools.

Configure CloudBase credentials through the authentication flow or an API key, then select the target environment before using resource tools. Local build workflows require a local MCP mode because they read project files or build contexts. Personal TCR image builds may use TCB_TCR_USERNAME and TCB_TCR_PASSWORD in a local MCP configuration that supports custom environment variables. Enterprise image builds instead require account-level credentials capable of obtaining a CAM-backed temporary token.

Tools and capabilities

Supported areas include:

  • Inspecting environments, usage, metrics, domains, runtime backends, and billing-related information.
  • Reading and managing NoSQL collections, indexes, records, data models, PostgreSQL, MySQL, and storage.
  • Listing functions, logs, layers, versions, aliases, and triggers; creating, deploying, invoking, and routing functions.
  • Uploading and managing static-hosting files, website configuration, custom domains, Cloud Run services, and gateway routes.
  • Downloading React, Vue, WeChat Mini Program, UniApp, or editor-configuration templates.
  • Searching CloudBase documentation, skills, and OpenAPI definitions.
  • Planning and applying project-level deployments from cloudbaserc.

PostgreSQL environments require special care: queryPgStorage is for the PG storage path, while the older storage tools target the conventional NoSQL/COS storage system. Environment inspection also reports whether PostgreSQL, NoSQL, and MySQL backends are available so an agent can choose an applicable database path.

Limitations and notes

The tools operate within CloudBase permissions and credential scope. They do not infer that a missing environment exists in another region when the current credential cannot see it. Static hosting domains, gateway custom domains, and environment security domains are separate concepts: security domains configure browser CORS origins, while gateway tools configure HTTP entry points.

Temporary storage URLs expire, and derived public URLs only work for publicly readable buckets. Server-side NoSQL writes do not automatically add _openid, which can affect client-side row-level access rules. Cloud function layers use an account-level namespace, so layer names should include the current environment identifier. Finally, deployment and destructive operations should be reviewed rather than treated as automatically safe.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about CloudBase AI ToolKit

TencentCloudBase/CloudBase-AI-ToolKit is an MCP server that connects AI coding tools to Tencent CloudBase environments. Its main tools authenticate and bind environments, query and manage databases, functions, storage, hosting, Cloud Run, gateways, documentation, and project deployments, with confirmation controls for sensitive changes.

Install or run it with `npx @cloudbase/cloudbase-mcp@latest`, then add the MCP configuration to an MCP-capable IDE. The repository also documents plugin and marketplace installation paths for some coding tools. After setup, authenticate with CloudBase and bind a target environment.

Yes, Cursor is named as a supported AI coding tool in the repository. You can use the MCP configuration path or the relevant CloudBase plugin workflow, then authenticate and bind an environment before calling CloudBase tools.

Use `deployPlan` first to preview the `cloudbaserc` deployment, then use `deployApply` with `confirm=true` to execute it. The workflow can process database, function, app, hosting, and gateway resources, and destructive database migrations additionally require `confirmDestructive=true`.

Yes, it provides separate tools for CloudBase PostgreSQL and NoSQL operations. PostgreSQL tools support metadata inspection, read-only SQL, migrations, writes, and RLS-related SQL; NoSQL tools manage collections, indexes, records, and data structure. The environment’s available backends should be checked first.

Related MCP servers

All in Cloud Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCloudBase AI ToolKit AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/tencentcloudbase-cloudbase-ai-toolkit?style=directory)](https://allmcps.com/mcp/tencentcloudbase-cloudbase-ai-toolkit)
HTML Embed
<a href="https://allmcps.com/mcp/tencentcloudbase-cloudbase-ai-toolkit"><img src="https://allmcps.com/api/badge/tencentcloudbase-cloudbase-ai-toolkit?style=directory" alt="CloudBase AI ToolKit on AllMCPs" /></a>