How do I set up the Arrakis MCP server?
Clone the repository and add the following to your MCP client configuration: `"arrakis": { "command": "<path-to-uv>", "args": ["--directory", "<path-to-repo>", "run", "arrakis_mcp_server.py"] }`.
@abshkbh
基本信息
MCP server for https://github.com/abshkbh/arrakis
Start a new VM sandbox
Restore a VM from a snapshot
Create a snapshot of a VM
Run a command in a VM
Upload a file to a VM
Download a file from a VM
Destroy a specific VM
Destroy all VMs
Update the state of a VM (pause/stop)
The Arrakis MCP Server is a Model Context Protocol (MCP) server that exposes Arrakis VM sandbox functionality to Large Language Models. It allows LLMs to manage virtual machines, run commands, upload/download files, and control VM state via MCP tools and resources.
Clone the repository, then configure your LLM tool to use the Arrakis MCP server by adding it to your MCP configuration with uv as the command and arrakis_mcp_server.py as the entry point. After setup, the server provides MCP resources and tools for VM management.
arrakis://vms resource.arrakis://vm/{vm_name}.Clone the repository and add the following to your MCP client configuration: `"arrakis": { "command": "<path-to-uv>", "args": ["--directory", "<path-to-repo>", "run", "arrakis_mcp_server.py"] }`.
It provides tools: `start_sandbox`, `restore_snapshot`, `snapshot`, `run_command`, `upload_file`, `download_file`, `destroy_vm`, `destroy_all_vms`, and `update_vm_state`.
Two resources: `arrakis://vms` (list all VMs) and `arrakis://vm/{vm_name}` (get specific VM information).
It is licensed under the GNU Affero General Public License v3.0.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Model Context Protocol Servers
Painless E2E Automation for Mobile and Web
MCP Toolbox for Databases is an open source MCP server for databases.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
评论