Control iTerm Terminal with LLMs
MCP server that provides AI models access to your iTerm terminal, enabling them to run commands, read output selectively, and control REPLs with full terminal
Why it matters
Empower Large Language Models to interact directly with your iTerm2 terminal. This allows LLMs to execute commands, read output, and control terminal applications, enabling sophisticated automation and analysis.
Outcomes
What it gets done
Execute commands in your iTerm terminal via LLM prompts.
Read and analyze terminal output for LLM-driven insights.
Interact with REPLs and send control characters (e.g., Ctrl+C) for full terminal control.
Delegate complex tasks to LLMs and observe their step-by-step execution within the terminal.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-iterm-mcp | bash Capabilities
Tools your agent gets
Writes to the active iTerm terminal, commonly used to execute commands.
Reads the requested number of lines from the active iTerm terminal.
Sends a control character to the active iTerm terminal.
Overview
iTerm MCP Server
What it does
A Model Context Protocol server that connects AI models to your active iTerm2 terminal session through three tools for writing commands, reading output, and sending control characters.
How it connects
Use when you want to share your iTerm terminal with an AI model for command execution and output inspection. The source emphasizes that users must monitor activity and abort when appropriate, as the server makes no attempt to evaluate command safety. Start with smaller tasks until familiar with model behavior.
Source README
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.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.