mcp-sandbox-server
mcp-sandbox-server
一个远程 MCP(模型上下文协议)服务器,为 AI 代理提供对沙箱主机的经过认证的 shell 和文件访问权限——此外还提供一条安全、受限的路径,用于在它本不应拥有完全访问权限的独立生产主机上触发部署。
功能
核心 MCP 工具(
run_command、read_file、write_file、list_directory)通过 Streamable HTTP 暴露,使代理可以直接在沙箱上构建和测试代码。一个极简的 OAuth 2.1 授权服务器,从零构建:支持动态客户端注册(RFC 7591)、由单一管理员凭据保护的授权端点,以及带 PKCE 的令牌端点。之所以存在,是因为 MCP 客户端(如 claude.ai 的连接器界面)期望完整的 OAuth 流程,而不是粘贴的 bearer token——因此服务器必须支持它,即使只是单管理员场景。
一个通往第二台更敏感主机的受限网关(
biscuit_status、biscuit_logs、biscuit_deploy等)。与其仅依赖工具代码来约束代理的行为边界,真正的边界被下放到更底层:目标主机上authorized_keys中通过command="..."限制的专用 SSH 密钥,确保无论客户端通过该密钥发送什么,都只能执行一个固定的、白名单内的脚本。这里的工具代码只是构造字面操作字符串——它并非安全边界,强制命令才是。
Related MCP server: Shellgate
构建原因
有趣的约束在于:同一个代理需要两种截然不同的信任级别——在可丢弃的沙箱上拥有完全、不受限制的 shell 权限,但在运行着实时服务的主机上只能执行少量预先批准、以读取为主的操作。与其试图对代理的行为进行沙箱化(通过提示词、工具描述等方式),设计将真正的边界下沉到操作系统层面强制执行的位置——无论代理决定发送什么,都受强制 SSH 命令和带路径穿越检查的白名单脚本约束。
技术栈
Node.js、Express、@modelcontextprotocol/sdk、Zod。无数据库——认证状态持久化在服务器旁边的一个小型 JSON 文件中。
说明
这是一个经过精简和标识符脱敏的生产环境真实服务器副本。真实主机名、IP 地址和内部项目名称均已替换为占位符(your-production-server-ip、project-a/project-b/project-c 等)。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityAmaintenanceProvides policy-driven, auditable SSH access to server fleets for AI assistants with zero-trust security controls, command whitelisting, and comprehensive audit logging to safely manage infrastructure.1327Apache 2.0
- AlicenseNot gradedqualityAmaintenanceA secure gateway that lets AI agents interact with APIs and SSH servers via scoped tokens, with credential injection, human-in-the-loop for dangerous commands, and MCP integration for tool access.1015MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to securely execute SSH commands on remote servers with connection pooling, session isolation, and a web audit panel.3MIT
- AlicenseAqualityCmaintenanceEnables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.5MIT
Related MCP Connectors
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
The bridge from K2 agents through Wrangler to your master AI - safe, approval-gated Cloudflare ops.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/enes-sakin-dev/mcp-sandbox-server-showcase'
If you have feedback or need assistance with the MCP directory API, please join our Discord server