A Model Context Protocol (MCP) server that exposes Arrakis VM sandbox functionality to Large Language Models.
Clone this repository:
git clone https://github.com/abshkbh/arrakis-mcp-server.git
cd arrakis-mcp-server
Configure your LLM tool to use the Arrakis MCP server by adding the following to your MCP configuration:
"mcpServers": {
"arrakis": {
"command": "<path-to-uv>",
"args": [
"--directory",
"<path-to-repo>",
"run",
"arrakis_mcp_server.py"
]
}
}
The Arrakis MCP Server exposes the following MCP resources and tools:
arrakis://vms
- List all available VMsarrakis://vm/{vm_name}
- Get information about a specific VMstart_sandbox
- Start a new VM sandboxrestore_snapshot
- Restore a VM from a snapshotsnapshot
- Create a snapshot of a VMrun_command
- Run a command in a VMupload_file
- Upload a file to a VMdownload_file
- Download a file from a VMdestroy_vm
- Destroy a specific VMdestroy_all_vms
- Destroy all VMsupdate_vm_state
- Update the state of a VM (pause/stop)This project is licensed under the GNU Affero General Public License v3.0 - see the LICENSE file for details.
{
"mcpServers": {
"arrakis": {
"env": {},
"args": [
"--directory",
"<path-to-repo>",
"run",
"arrakis_mcp_server.py"
],
"command": "uv"
}
}
}
Seamless access to top MCP servers powering the future of AI integration.