MCP Terminal Server

@RinardNick

代码仓库

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

RinardNick

关于 MCP Terminal Server

An MCP server that provides secure terminal access for Claude and other LLMs

#mcp-terminal#secure-terminal#mcp

MCP Terminal Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-terminal": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

MCP Terminal Server 工具

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。

概览

What is MCP Terminal Server?

MCP Terminal Server is a secure terminal execution server implementing the Model Context Protocol (MCP). It provides controlled command execution capabilities with security features and resource limits, designed for use with MCP-based applications like Claude Desktop.

How to use MCP Terminal Server?

Install the package using uv pip install mcp-terminal, then configure Claude Desktop with the command and args fields, specifying allowed commands, timeout, and maximum output size. The server can also be tested with the MCP Inspector tool.

Key features of MCP Terminal Server

Execute shell commands with output capture and error handling
Restrict allowed commands and prevent command injection
Command timeouts and maximum output size limits
Standard MCP message format with capability advertisement
Streaming output support for long-running commands

Use cases of MCP Terminal Server

Running development commands (git, pip, python, ls, cd) through Claude Desktop
Executing controlled shell commands from AI agents via MCP
Automating terminal tasks with enforced security boundaries and resource protection

常见问题

What commands are allowed by default?

The server does not allow any commands by default; you must specify the allowed commands using the `--allowed-commands` argument.

What are the runtime dependencies?

MCP Terminal Server requires Python and the `uv` package manager. It is designed to work with MCP clients such as Claude Desktop.

How are commands protected from injection?

The server validates commands against a whitelist, blocks shell operators, and prevents command injection attempts.

What resource limits are enforced?

Each command has a configurable timeout (default 30 seconds) and a maximum output size (default 1 MB) to prevent hanging or memory exhaustion.

How does the server communicate?

It implements the Model Context Protocol version 1.0.0, using JSON messages over standard input/output (stdio) with the client.

开发工具分类下的更多 MCP 服务器

Mcp-Warden

ermoluk

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.

Innovalyxx Sovereign Edge

edge.innovalyxx.com

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

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

Foremerge

naw103

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