← Back to Skills Marketplace
172
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install yunxiao-devops-mcp
Description
阿里云云效 MCP 操作工具。通过 MCP SSE 协议操作云效平台，支持项目管理、工作项管理、流水线管理、代码仓库等 165+ 工具。
Usage Guidance
This skill appears to be a local MCP SSE client and is internally consistent. Before installing or running it:
- Do not hand your Alibaba Cloud RAM AccessKey/Secret to the agent; if you deploy the MCP Server (DEPLOY.md), follow the doc and perform deployment manually. The server Docker image will require those credentials.
- Review and verify the Docker image source (build-steps-public-registry.cn-beijing...) before running it.
- npm install will fetch a public dependency (eventsource-parser); run installs in a controlled environment and review dependencies if you have strict supply-chain requirements.
- The client talks to a user-configurable baseUrl (defaults to localhost:3000). Ensure you only point it at a server you trust.
If you want higher assurance, ask for: the publisher identity, a signed release or official upstream repo, and an audit of the Docker image used by the MCP Server.
Capability Analysis
Type: OpenClaw Skill
Name: yunxiao-devops-mcp
Version: 1.2.1
The skill bundle provides a legitimate Node.js client for interacting with an Alibaba Cloud Yunxiao (DevOps) MCP server via the SSE protocol. The core logic in `client/src/client.mjs` and the CLI in `client/src/cli.mjs` strictly follow the Model Context Protocol (MCP) specification for tool discovery and execution. The documentation in `DEPLOY.md` and `SKILL.md` includes appropriate security warnings regarding the manual handling of cloud credentials and provides clear, non-malicious instructions for AI agents to operate the 165+ supported DevOps tools.
Capability Assessment
Purpose & Capability
The name/description match the provided client code and SKILL.md: this is an MCP SSE client that talks to a local MCP Server (default http://localhost:3000) and exposes 165+ tools. There are no unrelated environment variables or binaries declared. The need for Alibaba Cloud credentials appears only in DEPLOY.md for the separate MCP Server image (reasonable and documented).
Instruction Scope
Runtime instructions only cover installing the Node client (npm install), starting/pointing to a local MCP Server, listing tools, querying schemas, and calling tools. The DEPLOY.md explicitly instructs that server deployment must be performed manually and that AI agents must not run the deployment commands. The SKILL.md and client code do not read arbitrary host files or exfiltrate data to external endpoints other than the configured MCP Server.
Install Mechanism
The registry entry has no automated install spec; the package includes a Node.js client whose installation is via npm (client recommends npm install). That pulls one dependency (eventsource-parser) from the public npm registry — expected for a Node client but worth noting as a standard third-party dependency fetch.
Credentials
The skill itself declares no required env vars or credentials. DEPLOY.md (separate MCP Server) requires ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET for server deployment; this is appropriate for a server that needs to access Alibaba Cloud, but these credentials are sensitive and the docs explicitly require manual, human-driven deployment rather than automated use by the agent.
Persistence & Privilege
No elevated privileges are requested. always is false, the skill does not request persistent insertion into agent configs, and it does not modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install yunxiao-devops-mcp - After installation, invoke the skill by name or use
/yunxiao-devops-mcp - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.1
删除无用的代码，精简项目结构
v1.2.0
list 输出 Markdown 表格格式更省 token；新增 schema 命令按需获取工具参数定义；新增典型 AI agent 调用流程指南
v1.1.0
客户端从 Python 改为 Node.js，新增 --stdin 参数支持大参数传递
v1.0.0
Initial release: 阿里云云效 MCP 操作工具，支持项目管理、工作项、流水线、代码仓库等 165+ 工具
Metadata
Frequently Asked Questions
What is 云效 DevOps MCP?
阿里云云效 MCP 操作工具。通过 MCP SSE 协议操作云效平台，支持项目管理、工作项管理、流水线管理、代码仓库等 165+ 工具。 It is an AI Agent Skill for Claude Code / OpenClaw, with 172 downloads so far.
How do I install 云效 DevOps MCP?
Run "/install yunxiao-devops-mcp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 云效 DevOps MCP free?
Yes, 云效 DevOps MCP is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 云效 DevOps MCP support?
云效 DevOps MCP is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 云效 DevOps MCP?
It is built and maintained by JonasGao (@jonasgao); the current version is v1.2.1.
More Skills