TencentCloudBase/CloudBase-AI-Toolkit#dsh-plugin
Tencent CloudBase backend for DeepSeek Harness — scaffold and deploy full-stack apps from chat, render query results as table cards with paging, sorting and CSV export, preview a deployment on its domain, and call the CloudBase MCP toolset (`mcp__cloudbase__*`) with device-code login.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — DeepSeek Harness plugin integrating Tencent CloudBase backend. Supports scaffolding and deploying full-stack apps from chat, rendering query results as table cards, and calling CloudBase MCP toolset.
Who it is for — Suitable for users developing full-stack applications with DeepSeek Harness who need cloud backend scaffolding and deployment support.
Those not requiring integration with Tencent CloudBase databases, storage, or deployments can skip it.
Watch out — After npm install, it registers successfully in a fresh profile and gets enabled by Harness. It executes shell commands but sandbox testing passes. No obvious issues found.
The verdict — If you're already running backend services on Tencent CloudBase, I would install it for the direct MCP toolset and deployment preview integration.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-plugin is a DeepSeek Harness plugin that connects chat-driven development to Tencent CloudBase’s backend services. DeepSeek Harness loads a CloudBase MCP bridge together with Agent Skills and Hooks, providing the mcp__cloudbase__* toolset for database, storage, authentication, functions, hosting and deployment operations. Login uses a device-code flow, and the toolkit expects a CloudBase environment of its own.
From a conversation, dsh-plugin can scaffold and deploy full-stack applications, query or change CloudBase data, and render query results as table cards with paging, sorting and CSV export. After deployment, the application can be previewed on its CloudBase domain. The integration also includes a DB/Storage/Auth panel. Its terminal surface is used to install or run the MCP tooling, and the resulting operations can act on CloudBase resources with the agent’s available permissions.
dsh-plugin is intended for developers already using CloudBase as the backend for an AI coding workflow. It is a poor fit when no CloudBase environment is available, when only framework knowledge is needed, or when backend changes should not be proposed or executed through an agent. The README explicitly advises confirming sensitive actions proposed by the AI.
DeepSeek Harness loads dsh-plugin as an integration layer for CloudBase. The package combines an MCP server, Agent Skills and Hooks, then exposes CloudBase operations through tools named mcp__cloudbase__*. The README describes operations for login, data queries and changes, functions, hosting, storage, logs and deployment. It also describes a DB/Storage/Auth panel for the DeepSeek Harness interface.
Authentication uses a device-code login flow. The toolkit connects to a CloudBase environment supplied by the developer; the README does not document a default environment or a default region. Sensitive actions still require review before they are allowed to proceed.
The README identifies these configuration values:
| Identifier | Purpose |
|---|---|
lang |
Sets the instance-level tool language. |
auth.site |
Selects the authentication site. |
auth.region |
Selects the authentication region. |
envId |
Identifies the CloudBase environment. |
region |
Selects the CloudBase region. |
site |
Selects the CloudBase site. |
envId, region and site can be supplied through cloudbaserc.json as field-level fallbacks. Values may be literals or expressions such as {{env.KEY}}. The README does not specify defaults for these values.
The MCP toolset can scaffold and deploy full-stack applications from chat, query data and render results as table cards with paging, sorting and CSV export. It can also manage database, storage, authentication, functions and hosting resources, read logs, and preview a deployment on its CloudBase domain.
A CloudBase environment is required. dsh-plugin operates through the agent’s permissions and includes a terminal surface for the MCP tooling, so proposed sensitive changes should be confirmed. Developers who only need CloudBase guidance rather than operational access may prefer the separate Skills collection described by the README.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
Tencent
Four read-only tools over a WeKnora knowledge base: list knowledge bases, hybrid passage search, reassemble one document's chunks in order, and WeKnora's own cited RAG or ReAct-agent answer with a resumable session id.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
superdesigndev
Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.
Installed cleanly when we ran it
sixtysevenlf
Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.
Installed cleanly when we ran it
yjl9903
Anime Garden for DSH: search anime torrent resources from 動漫花園, 蜜柑计划, 萌番组 and ANi inside DSH — via chat, a sidebar panel with fansub and type filters, a seasonal calendar, and an in-app floating player.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
Lum1104
Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.
Installed cleanly when we ran it
anysearch-team
AnySearch-powered real-time web and vertical search provider for DeepSeek Harness.
Installed cleanly when we ran it
