What security measures does mcp_shell_server implement?
The server includes safeguards such as command restrictions, output length limits, and execution timeouts to prevent abuse and manage risks.
@JMReader
基本信息
An MCP server capable of executing any terminal command securely and efficiently
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
mcp_shell_server is an MCP (Model Context Protocol) server that enables the secure and efficient execution of arbitrary shell commands from connected clients. It provides a flexible interface between language models and the underlying operating system, exposing system-level resources such as platform, hostname, and shell path. This server is intended for developers building AI agent systems that require shell access.
The README does not provide specific installation or invocation steps. Usage requires a Python environment with the MCP protocol library. The server is designed to be easily integrated with popular MCP clients or embedded within larger AI agent systems.
The server includes safeguards such as command restrictions, output length limits, and execution timeouts to prevent abuse and manage risks.
mcp_shell_server is compatible with Linux, macOS, and Windows (using CMD or PowerShell).
The server is built with Python and uses the MCP protocol. A Python environment with the necessary MCP library is required.
Yes, it exposes system-level resources including platform name, hostname, shell path, and environment details.
The server is designed for easy integration with MCP clients, but specific connection instructions (e.g., transport type) are not detailed in the README.

AdsMCP is the MCP entry point into the Adgentek Ad Server. Call ads_serve with the conversation context and get back a native ad matched to user intent, or no ad when one does not fit. Publishers earn on a CPM basis. Fre

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Open-source Next.js + Supabase CMS with a per-site MCP server: scaffold a site, then create pages, posts, navigation, media and SEO from Claude, Cursor or any MCP client. Streamable HTTP with a bearer token you mint in y
评论