CloudStack MCP
About
proof of concept MCP server for apache cloudstack
Details
- Author
- walteh
- Downloads
- 292
- Categories
- Other
Jump to
- Translates MCP protocol requests into CloudStack API calls
- Provides common operations like VM deployment and management
- Handles authentication and API interaction automatically
- Supports both SSE and stdio transports
- Includes a containerized CloudMonkey CLI for manual CloudStack commands
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
CloudStack MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies (brew install go-task go docker), clone the repository, and start the environment with task docker:start. Then configure your MCP client (Cursor or Claude Desktop) to connect via SSE (http://localhost:8250/sse) or stdio (using docker compose). Detailed setup instructions for both clients are provided in the README.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"cloudstack mcp": {
"cloudstack": {
"type": "http",
"url": "http://localhost:8250/sse"
}
}
}
}
McpServers
{
"cloudstack": {
"type": "http",
"url": "http://localhost:8250/sse"
}
}
CloudStack MCP
A Model Context Protocol (MCP) server for Apache CloudStack, allowing AI agents to interact with CloudStack infrastructure.
> [!IMPORTANT]
> This project is still under development and not all features are available. Treat it as a proof of concept.
Running the server (macOS)
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



