What are the dependencies for running CloudStack MCP?
On macOS, you need `brew install go-task go docker`. Additionally, to use the server with an MCP client, you may need Cursor or Claude Desktop.
@walteh
Basic information
proof of concept MCP server for apache cloudstack
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cloudstack": {
"type": "http",
"url": "http://localhost:8250/sse"
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list directly from this server's endpoint using the button above.
CloudStack MCP is a Model Context Protocol (MCP) server for Apache CloudStack that allows AI agents to interact with CloudStack infrastructure. The project is under development and is a proof of concept, so not all features are available yet.
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.
On macOS, you need `brew install go-task go docker`. Additionally, to use the server with an MCP client, you may need Cursor or Claude Desktop.
Run `task docker:start` from the repository root. The server will expose an SSE endpoint on port 8250.
No. The project is under development and is a proof of concept. Many features are not yet available.
It supports SSE (recommended) and stdio. JSON configuration examples for both transports are provided in the README.
The README warns there is a 99% chance it will not work with Claude Desktop, but provides a starting point for configuration via `task mcp:setup:claude-desktop`.
A curated list of references for MLOps
不止于 CSS
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Comments