Happy slice of mcp pizzaMCP.pizza

iterm-mcp

MCP.Pizza Chef: ferrislucas

It shares your live iTerm2 window on a Mac with the model, which can type commands into it, read back just the last few lines of output, and send key presses such as Ctrl-C to stop something. You watch every step happen in the window you already use, which suits a long-running job or an interactive session like a Python or database prompt. There are no built-in limits on what it may run, so keep an eye on it.

Unmaintained · No commits in 12 months.
Coding

Use This MCP server To

Ask what the error on my screen means Have the assistant run the next command for me Step through a build and watch each command Stop a runaway command with Ctrl-C Work through an interactive Python session together

README

iterm-mcp

A Model Context Protocol server that provides access to your iTerm session.

Main Image

Features

Efficient Token Use: iterm-mcp gives the model the ability to inspect only the output that the model is interested in. The model typically only wants to see the last few lines of output even for long running commands.

Natural Integration: You share iTerm with the model. You can ask questions about what's on the screen, or delegate a task to the model and watch as it performs each step.

Full Terminal Control and REPL support: The model can start and interact with REPL's as well as send control characters like ctrl-c, ctrl-z, etc.

Easy on the Dependencies: iterm-mcp is built with minimal dependencies and is runnable via npx. It's designed to be easy to add to Claude Desktop and other MCP clients. It should just work.

Safety Considerations

  • The user is responsible for using the tool safely.
  • No built-in restrictions: iterm-mcp makes no attempt to evaluate the safety of commands that are executed.
  • Models can behave in unexpected ways. The user is expected to monitor activity and abort when appropriate.
  • For multi-step tasks, you may need to interrupt the model if it goes off track. Start with smaller, focused tasks until you're familiar with how the model behaves.

Tools

  • write_to_terminal - Writes to the active iTerm terminal, often used to run a command. Returns the number of lines of output produced by the command.
  • read_terminal_output - Reads the requested number of lines from the active iTerm terminal.
  • send_control_character - Sends a control character to the active iTerm terminal.

Requirements

  • iTerm2 must be running
  • Node version 18 or greater

Installation

To use with Claude Desktop, add the server config:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

iterm-mcp FAQ

What do I need?
A Mac running iTerm2 and Node 18 or newer. There is no account or key.
Which apps does this work in?
Claude Desktop is documented, and other MCP clients work from the same short settings block.
Can I use this to debug an error I am staring at?
Yes — it reads what is on screen and can run the next command itself.
Is it safe?
There are no built-in restrictions on what it may run, so watch it and interrupt if it goes off track.
Does it work on Windows or Linux?
No. It drives iTerm2, which is macOS only.
Is it still maintained?
The last update was September 2025. It is small and still works, but it is not moving quickly.