What are the required configuration fields?
The `allowedCommands` list, `defaultTimeout`, and `defaultCwd` are configurable; the README shows `npm`, `node`, and `git` as examples for allowed commands and a 30-second timeout.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-terminal"
]
}
}
}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。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
A terminal server implementation for the Model Context Protocol (MCP). It provides secure and controlled access to shell commands and npm operations, designed for MCP integrations that need to run terminal tasks programmatically.
Install the package via npm, then add the provided JSON configuration to your MCP config file. The configuration defines allowed commands, a default timeout, a working directory, and environment variables.
The `allowedCommands` list, `defaultTimeout`, and `defaultCwd` are configurable; the README shows `npm`, `node`, and `git` as examples for allowed commands and a 30-second timeout.
It restricts which commands can be run via the `allowedCommands` configuration array—only those listed (e.g., `npm`, `node`, `git`) are permitted.
The server exposes `install()`, `runScript()`, `dev()`, and `build()` methods for common npm tasks like installing packages and running scripts.
Yes, you can set environment variables like `NODE_ENV` through the `environmentVariables` configuration object.
It requires Node.js and npm to be installed, and it is installed via `npm install @modelcontextprotocol/server-terminal`.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
评论