CloudStack MCP
About
proof of concept MCP server for apache cloudstack
Details
- License
- Apache-2.0 license
Explore
- 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
brew install go-task go docker
git clone https://github.com/walteh/cloudstack-mcp.git
cd cloudstack-mcp
task docker:start
1. make sure server is running and you are in the root of the project (see above)
2. set up dependencies
brew install --cask cursor
3. open the project in Cursor
cursor cloudstack-mcp.code-workspace
4. open cursor settings from the menu bar Cursor -> Settings... -> Cursor Settings (or press Shift-Cmd-J)
5. go to the MCP tab, you should see the cloudstack server already added (because of ./.cursor/mcp.json)
6. click on the buttons to refresh and enable the cloudstack server - you should see a green dot and a list of list cloudstack api commands
7. open a new composer by making sure the composer pane is open (toggle with Cmd-Option-B) and start a new conversation (press Cmd-N)
8. make sure the composer is set to Agent
9. type can you list my @cloudstack vpcs?
10. press Enter and watch the magic happen!
> [!CAUTION]
> There is a 99% chance this will not work, but you can use it as a starting point to get the MCP working with Claude Desktop if you like.
1. make sure server is running and you are in the root of the project (see above)
2. set up dependencies
bashbrew install --cask claude-desktop
3. run this to setup the server in Claude Desktop
bash
task mcp:setup:claude-desktop
4. restart claude desktop
CloudMonkey (the CloudStack CLI) is containerized in this setup:
bashClaude 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"
}
}
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.



