microsandbox-mcp
Connects AI agents to microsandbox for creating lightweight sandboxes, executing code, managing files, and monitoring resources.
README
microsandbox-mcp
Give your AI agents sandboxes. This MCP server connects any AI agent to microsandbox — letting them create fast lightweight sandboxes, execute code, manage files, and monitor resources.
Documentation | npm Package | GitHub
Installation
Run the server with npx -y microsandbox-mcp using stdio transport.
<details> <summary><b>Claude Code</b></summary>
claude mcp add --transport stdio microsandbox -- npx -y microsandbox-mcp
</details>
<details> <summary><b>Cursor</b></summary>
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"microsandbox": {
"command": "npx",
"args": ["-y", "microsandbox-mcp"]
}
}
}
</details>
<details> <summary><b>VS Code</b></summary>
Add to .vscode/mcp.json:
{
"servers": {
"microsandbox": {
"command": "npx",
"args": ["-y", "microsandbox-mcp"]
}
}
}
</details>
<details> <summary><b>Claude Desktop</b></summary>
Add to your config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"microsandbox": {
"command": "npx",
"args": ["-y", "microsandbox-mcp"]
}
}
}
</details>
<details> <summary><b>Windsurf</b></summary>
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"microsandbox": {
"command": "npx",
"args": ["-y", "microsandbox-mcp"]
}
}
}
</details>
<details> <summary><b>Zed</b></summary>
Add to your Zed settings:
{
"context_servers": {
"microsandbox": {
"command": {
"path": "npx",
"args": ["-y", "microsandbox-mcp"]
}
}
}
}
</details>
<details> <summary><b>Other Clients</b></summary>
For any MCP client that supports stdio transport:
{
"mcpServers": {
"microsandbox": {
"command": "npx",
"args": ["-y", "microsandbox-mcp"]
}
}
}
</details>
Available Tools
Sandbox Lifecycle:
| Tool | Description |
|---|---|
sandbox_run |
Create an ephemeral sandbox, run a command, return the output, and destroy it |
sandbox_create |
Create and boot a persistent named sandbox with full configuration |
sandbox_list |
List all sandboxes with their current status |
sandbox_inspect |
Get detailed sandbox information including full configuration |
sandbox_stop |
Stop a running sandbox (graceful SIGTERM or force SIGKILL) |
sandbox_remove |
Remove a stopped sandbox |
Command Execution:
| Tool | Description |
|---|---|
sandbox_exec |
Execute a command with arguments inside a running sandbox |
sandbox_shell |
Execute a shell command string with pipes, redirects, and shell syntax |
Filesystem:
| Tool | Description |
|---|---|
sandbox_fs_read |
Read a file from the sandbox filesystem |
sandbox_fs_write |
Write content to a file inside the sandbox |
sandbox_fs_list |
List directory contents |
sandbox_fs_mkdir |
Create a directory with parent directories |
sandbox_fs_remove |
Remove a file or directory |
sandbox_fs_stat |
Get file metadata (kind, size, mode, modified time) |
Volume Management:
| Tool | Description |
|---|---|
volume_create |
Create a named persistent volume that survives sandbox restarts |
volume_list |
List all volumes |
volume_remove |
Remove a named volume |
Monitoring:
| Tool | Description |
|---|---|
sandbox_metrics |
Get live CPU, memory, disk I/O, and network metrics |
check_installed |
Verify that the msb runtime and libkrunfw are available |
Requirements
macOS (Apple Silicon) or Linux (x86_64/ARM64 with KVM support).
The msb runtime and libkrunfw are installed automatically on first run. If that fails, install manually:
curl -fsSL https://install.microsandbox.dev | sh
Development
git clone https://github.com/superradcompany/microsandbox-mcp.git
cd microsandbox-mcp
npm install
npm run build
node dist/index.js
Links
- microsandbox — The microVM sandbox runtime
- Documentation — Guides and API reference
- Agent Skills — Teach agents to use microsandbox without MCP
License
Apache-2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。