Iterm Mcp

What is Iterm Mcp about?

Iterm Mcp enables an AI model to interact directly with an active iTerm2 terminal. It can run commands, fetch specific lines of output, and send control characters such as Ctrl‑C or Ctrl‑Z, allowing the model to operate like a human user inside the shell.

How to use Iterm Mcp?

1. Install: Ensure iTerm2 is running and Node ≥ 18 is installed.
2. Add to Claude Desktop (or any MCP client) by editing the client’s claude_desktop_config.json and adding:

   {
     "mcpServers": {
       "iterm-mcp": {
         "command": "npx",
         "args": ["-y", "iterm-mcp"]
       }
     }
   }
   

3. Start the server via the client; the server communicates over stdio.
4. Use the provided tools (write_to_terminal, read_terminal_output, send_control_character) in your prompts to let the model control the terminal.
5. For development, clone the repo, run yarn install, then yarn run build (or yarn run watch for auto‑rebuild). Debug with the MCP Inspector (yarn run inspector).

Key features of Iterm Mcp

• Efficient token usage – fetch only the lines the model needs instead of the whole screen.
• Full terminal control – start REPLs, execute commands, and send any control characters.
• Minimal dependencies – runnable with a single npx command, no heavy setup.
• Easy integration – works out‑of‑the‑box with Claude Desktop and other MCP clients.
• Cross‑platform config – configuration files for macOS and Windows are provided.

Use cases of Iterm Mcp

• Interactive debugging – ask the model to run a command, view the last few lines of output, and suggest fixes.
• REPL assistance – let the model drive a Python, Node, or Ruby REPL, typing code and reading results.
• CLI automation – delegate repetitive shell tasks (e.g., file manipulation, git operations) to the model while you monitor.
• Learning environments – students can query the model about terminal state while experimenting.

FAQ from the Iterm Mcp

Q: Do I need any special permissions? A: The tool only requires that iTerm2 is running and that the user running the server has permission to control the terminal.

Q: Is there any safety built‑in to prevent dangerous commands? A: No. The user is fully responsible for monitoring and aborting any unsafe activity.

Q: Can I use Iterm Mcp on Linux? A: It is designed for iTerm2, which is macOS‑only. Windows users can use the provided config path, but the underlying terminal must be iTerm2 via macOS.

Q: How do I debug communication issues? A: Use the MCP Inspector (yarn run inspector) which provides a web UI to view the stdio exchange between the client and server.

Q: What Node version is required? A: Node 18 or newer.

iterm-mcp

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

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

{
  "mcpServers": {
    "iterm-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "iterm-mcp"
      ]
    }
  }
}

Installing via Smithery

To install iTerm for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install iterm-mcp --client claude

Development

Install dependencies:

yarn install

Build the server:

yarn run build

For development with auto-rebuild:

yarn run watch

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

yarn run inspector
yarn debug <command>

The Inspector will provide a URL to access debugging tools in your browser.