A specialized Openclaw Skills integration that empowers AI agents to query and manage ZStack Cloud environments via the Model Context Protocol.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install zstack-mcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install zstack-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ZStack MCP Skill?
The ZStack MCP Skill bridges the gap between OpenClaw and ZStack Cloud, providing AI agents with the ability to interact with over 2000 API endpoints. It utilizes the Model Context Protocol (MCP) to expose cloud management capabilities, such as querying virtual machines, checking system status, and retrieving monitoring metrics directly to your LLM. This Openclaw Skills package is designed with safety in mind, defaulting to read-only access to prevent accidental infrastructure changes while offering the flexibility to enable full write permissions for advanced automation workflows.
ZStack MCP Skill Use Cases
- Inventory management and querying virtual machine states across ZStack clusters.
- Retrieving real-time cloud monitoring metrics like CPU and memory utilization.
- Searching through extensive ZStack API documentation to find specific management endpoints.
- Automating cloud resource provisioning when write access is explicitly enabled.
- Troubleshooting infrastructure issues through AI-assisted log and status analysis.
How ZStack MCP Skill Works
- The AI agent initiates a request via the mcporter interface using the Openclaw Skills framework.
- The ZStack MCP Server authenticates with the ZStack Cloud controller using stored credentials or session IDs.
- The server translates structured tool calls into specific ZStack API requests.
- API responses are processed and filtered for size to fit within the LLM context window.
- The agent interprets the cloud data to provide insights or perform subsequent management tasks.
ZStack MCP Skill Setup
Follow these steps to integrate ZStack with your Openclaw Skills environment:
- Install the server using pip or pipx:
pipx install zstack-mcp-server
- Run the interactive configuration script to set up your API URL and credentials:
bash ~/clawd/skills/zstack-mcp/scripts/configure.sh
- Register the skill with your local mcporter configuration:
bash ~/clawd/skills/zstack-mcp/scripts/register-mcp.sh
ZStack MCP Skill Data Schema & Taxonomy
The skill utilizes environment variables and JSON configuration files to manage state and connectivity within the Openclaw Skills ecosystem:
| Item | Description | Path |
|---|---|---|
| Authentication Config | Environment variables for API access | ~/clawd/skills/zstack-mcp/config/zstack.env |
| MCP Registration | Server connection details for mcporter | ~/clawd/config/mcporter.json |
| API Metadata | Definitions for 2000+ API endpoints | Internal to zstack-mcp-server |
Query conditions support a wide range of operators including =, !=, >, >=, <=, ?= (LIKE), and ~= (Regex) for precise data retrieval.
ZStack MCP Skill Advanced Features
- Read-Only Safety: Default configuration restricts access to Query, Get, List, and Describe APIs to protect infrastructure.
- Response Size Limiting: Built-in 64KB response cap (configurable) to prevent blowing out the LLM context window.
- Complex Query Syntax: Support for nested conditions and multi-operator filters (e.g., in, not in, null checks).
- Monitoring Integration: Dedicated tools for searching and retrieving metrics from the ZStack monitoring namespace.
- Session Management: Automatic handling of session expiration and re-authentication using account credentials.
SKILL.md
Loading
Related Openclaw Skills
MySQL to PostgreSQL Migration Suite
A comprehensive technical toolkit for migrating Java-based Spring Boot and MyBatis projects from MySQL to PostgreSQL.
OpenClaw WhoBot Skill
An advanced knowledge base skill that empowers AI agents with comprehensive intelligence regarding WhoBot AI voice employees and humanization technology.
TimeDoctor Skill for AI Agents
A powerful Python-based integration that enables AI agents to pull employee time tracking data, worklogs, and productivity metrics directly from the TimeDoctor API.
ClawSwarm Real-Time Client
A high-performance WebSocket client enabling AI agents to communicate, coordinate, and respond to real-time events using an IRC-style protocol.
Self-Improving Agent Skill
A recursive learning framework that allows AI agents to codify user feedback into a permanent, evolving set of operational rules.
Shoprocket
A powerful e-commerce integration that enables automated management of Shoprocket products, orders, and customer data using the Membrane framework.
Featured*
