CloudBase AI ToolKit

- CloudRun:getDeployLogfailures (CODING login / image deploy with no build) now rewrite togetProcessLog/getDeployRecordsnext steps instead of raw English errors

- Env: cross-region environment query and clearer credential-scope boundary for MCP auth
- Auth: drop redundantlogin_mode; keepcredential_scopeas the single credential boundary signal
- Release: Kimi plugin zip uses a whitelist-only, version-free asset name
- Kimi: plugin zip assembles sibling skills intoskills/cloudbase/references/so the archive stays self-contained and in sync with the manifest contract

- IDE: Kimi Code plugin (kimi.plugin.json) reuses shared CloudBase skills/MCP assets
- Release: pack Kimi plugin zip and attach it to GitHub Release assets automatically
- Auth UX: Kimi login via MCPauthdevice-code flow; routing skill loads domain knowledge on demand

AI IDEs (Cursor, Claude Code, Codex, CodeBuddy, and others) are strong at generating code. What usually blocks you is the backend: schemas, permissions, functions, storage, environments, and release.

This repository ships the npm package@cloudbase/cloudbase-mcp, Skills, and AI plugins.

You still need your own CloudBase environment, and you should confirm sensitive actions the AI proposes. The Toolkit provides capability and path—not judgment.

Prefer Plugin for the full stack; Skills alone when you only need knowledge constraints. For marketplace IDEs use this repo—do not also runnpx plugins addon the same tool.

Copy this AI prompt into your AI IDE. The agent readsskill.mdand completes the setup:

Set up CloudBase for me: 1. Open https://docs.cloudbase.net/skill.md and complete the setup following its instructions. 2. Tell me when you're done, and suggest the most relevant next step.

npx plugins add TencentCloudBase/cloudbase-plugin

Use CloudBase Skills to build a todo app with login, database and permissions, then deploy

Skills shape structure and practice; MCP handles environment and resources. You should be able to verify data and APIs in your own environment—not only get local source files.

After setup, the AI can do typical backend work in your environment (confirm critical steps):

- Database: PostgreSQL and document DB, data models, CRUD, permissions and security rules
- Compute: author, deploy, invoke, and debug cloud functions / Cloud Run
- Auth & storage: login methods, object storage, permission linkage with data
- Release & ops: static hosting / Mini Program publish; inspect logs and redeploy

Under controlled conditions, the same Todo application brief and frontend scaffold were used to compare two backend paths: a traditional cloud VM (self-managed runtime, process, and network exposure) and CloudBase (managed database, anonymous auth, and related backend services). An AI agent performed end-to-end development and verification. Given the model and task setup, the CloudBase path was more favorable in completion latency, token usage, and tool-call count. These outcomes are conditioned on the model, agent framework, and task definition, and should not be generalized beyond that scope.

Local(default):npxon your machine—full features, including local filesystem upload/templates.

Hosted: IDE connects over HTTP to Tencent Cloud MCP; no local Node. Some local-file features are unavailable.

{ "mcpServers": { "cloudbase": { "type": "http", "url": "https://tcb-api.cloud.tencent.com/mcp/v1?env_id=<env_id>", "headers": { "X-TencentCloud-SecretId": "<Tencent Cloud Secret ID>", "X-TencentCloud-SecretKey": "<Tencent Cloud Secret Key>" } } } }

Hosted URLs can usesite(domestic/intl) to pick the login site (e.g. domestic-site Singapore needssite=domestic), plusenable_plugins/disable_pluginsto trim tools. Canonical names live inmcp/src/server.ts.

Self-hosted Cloud Mode: setCLOUDBASE_MCP_CLOUD_MODE=true(orMCP_CLOUD_MODE=true) so local file and process tools are disabled for remote callers.

Those focus on shipping frontends or containers. CloudBase provides backend building blocks (database, auth, functions). The Toolkit lets AI tools use them in chat. Deploy is only part of the path.

Deploy targets your own CloudBase environment. In local mode MCP runs on your machine; code need not leave until you deploy. Cloud traffic uses HTTPS.

Localnpxis equivalent to running tools yourself. For remote hosts, setCLOUDBASE_MCP_CLOUD_MODE=trueto disable local file/process tools. Tencent Cloud hosted HTTP includes this protection.

Both the domestic site (cloud.tencent.com) and the international site (tencentcloud.com) offer theap-singaporeregion, so region alone is ambiguous. Without an explicit site, MCP defaults tointlforap-singapore(backward compatible). Domestic-site Singapore users must setTCB_SITE=domestic(together withTCB_REGION=ap-singapore) in the MCPenv, or add a.cloudbase/project.jsonat the project root:

{ "site": "domestic", "region": "ap-singapore", "envId": "your-env-id" }

Credentials are stored per site (credential.domestic/credential.intl) so domestic and international logins can coexist; legacy single-slotauth.jsonis read asdomesticand migrated on first write.

Hosted mode: addsite=domesticto the hosted URL (https://tcb-api.cloud.tencent.com/mcp/v1?env_id=<env_id>&site=domestic), since the URL is the only place hosted mode can carry the site (there is no MCPenvblock for HTTP servers).

Full-stack backend platform MCP — provision apps, manage databases, deploy functions, and more.

A template for deploying a remote, authentication-free MCP server on Cloudflare Workers. Tools are defined directly in the source code.

Deploy Python functions as web apps. Type hints become UI, API, and shareable links. 32 MCP tools for deploy, run, storage, secrets, scheduling, versioning, and sharing.

A template for deploying a remote MCP server on Cloudflare Workers without authentication.

Introspect and query your apps deployed to Convex.

Core AWS MCP server providing prompt understanding and server management capabilities.

An MCP service for deploying HTML content to EdgeOne Pages and obtaining a publicly accessible URL.

Create, build, deploy, and manage Netlify resources using natural language.

The Railway MCP Server enables natural language interaction with your Railway projects and infrastructure. Ask your IDE or AI assistant to create projects, deploy templates, manage environments, pull variables, redeploy services, and more.