Shell MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Shell MCP Server list files in current directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Shell MCP Server
Simple Model Context Protocol (MCP) server that exposes a single terminal tool for running shell commands.
Prerequisites
Python 3.11+
uv or
pip
Installation
uv sync
# or
pip install -e .Usage
Run the server over stdio:
python main.pyThe server registers a terminal tool. Invoke it with an object shaped like:
{
"command": "echo hello"
}Command output is returned as MCP TextContent. Errors are surfaced with a prefixed Error: message.
Resource
This server exposes a resource:
ID:
mcpreadme://desktopReturns the contents of
mcpreadme.mdresolved from OneDrive Desktop.
Resolution order:
$OneDrive/Desktop/mcpreadme.md~/OneDrive/Desktop/mcpreadme.md~/Desktop/mcpreadme.md
If the file is missing or unreadable, a textual error message is returned.
Docker
Build and run with uv inside the container (per uv Docker guide):
docker build -t shellserver .
docker run --rm -it shellserverThis image installs uv from the official image and uses:
Dependency caching layers via
uv sync --no-install-projectFinal run command equivalent to local:
uv run main.py
Reference: uv Docker integration docs: Installing a project
Available Tools
1 toolterminalD
Inputs: command (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no ambiguity about which tool to use.
With only one tool, naming consistency is not applicable; however, the name 'terminal' is a simple noun, which is acceptable but lacks a verb pattern.
A single tool for a shell server is too few; typical shell operations (e.g., run command, list files, manage processes) are all collapsed into one tool, making it overly broad and not well-scoped.
The tool surface is severely incomplete for a shell server, as it lacks explicit tools for common operations like file management, process control, or environment configuration, forcing the agent to rely on a single generic tool.
Related MCP Connectors
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables execution of shell commands through a terminal tool with working directory support and timeout protection. Also provides access to MCP documentation as a resource.-
- AlicenseBqualityDmaintenanceEnables execution of terminal commands, git operations, and automated setup of React, Vue, and Next.js projects with VSCode integration.775 npmMIT
- AlicenseAqualityCmaintenanceEnables secure command-line interactions on Windows systems with support for PowerShell, CMD, Git Bash, and WSL shells, providing controlled file access, command execution, and configurable security restrictions.636 npm4MIT
- FlicenseNot gradedqualityDmaintenanceEnables GPT Desktop to interact with local file systems and execute shell commands. Supports file operations (read, write, edit, delete), directory management, file search, and git status checks through natural language.-