Terminal MCP
Enables management of visible, interactive terminal sessions across platforms (macOS, Windows, Linux, WSL). Supports creating, executing commands, capturing output, and managing multiple terminal windows simultaneously.
README
Terminal MCP
Cross-platform MCP server for managing visible terminal sessions.
Features
- Cross-platform: Supports macOS, Windows, Linux, and WSL
- Visible terminals: Opens real terminal windows that users can see and interact with
- Multiple sessions: Manage multiple terminal sessions simultaneously
- Auto-cleanup: Automatically closes terminals when MCP server stops
Installation
Since this package is not published on PyPI, install it directly from the repository:
Option 1: Install from GitHub (recommended)
uv pip install "git+https://github.com/Hor1zonZzz/terminal-mcp.git"
Option 2: Install from a local clone
git clone https://github.com/Hor1zonZzz/terminal-mcp.git
cd terminal-mcp
uv pip install -e .
Usage
Claude Desktop Configuration
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"terminal": {
"command": "uv",
"args": ["run", "terminal-mcp"]
}
}
}
Or if installed globally:
{
"mcpServers": {
"terminal": {
"command": "terminal-mcp"
}
}
}
Available Tools
terminal_create_or_get
Create a new visible terminal window or get an existing one by name.
Parameters:
name(optional): Name for the terminal sessionworking_dir(optional): Working directory for the terminal
Returns: Session ID, name, platform, and status message
terminal_send_input
Send input (command or text) to a terminal.
Parameters:
session_id: The terminal session IDtext: The command/text to send
terminal_get_output
Get the output from a terminal.
Parameters:
session_id: The terminal session IDlines(optional): Number of lines to retrieve (default: 100, max: 1000)
terminal_list
List all active terminal sessions.
terminal_close
Close a terminal session.
Parameters:
session_id: The terminal session ID to close
Platform Support
| Platform | Terminal Used |
|---|---|
| macOS | Terminal.app (via AppleScript) |
| Windows | Windows Terminal (wt.exe) or cmd.exe |
| Linux | gnome-terminal, konsole, xfce4-terminal, xterm, etc. |
| WSL | Windows Terminal from WSL |
How It Works
- Terminal Creation: Opens a real terminal window using platform-specific methods
- Communication: Uses named pipes (Unix) or file polling (Windows) for bidirectional communication
- Output Capture: Logs terminal output to temporary files for retrieval
- Cleanup: Automatically closes all terminals when the MCP server stops (via atexit and signal handlers)
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.